Strata - Qwen3.8-Flash-Next on a normal PC (a GPU + system RAM + CPU)

=== Step 1: checking your PC ===
  Your AMD GPUs:
    GPU 0: AMD Radeon RX 6900 XT, 16 GB VRAM - can be used
  [ok] GPU: AMD Radeon RX 6900 XT, 16.0 GB VRAM, gfx1030 (AMD: docs/AMD_HIP.md)
  [ok] RAM: 128 GB
  [ok] CPU: AMD Ryzen Threadripper 3990X 64-Core Processor (AVX2)

=== Step 2: your choices ===
  [ok] model: Qwen3.8-Flash-Next Coder

  1) IQ1_M    the Coder's only size: half the experts, stored like IQ3_S (3.5 bits); download 58 GB, uses ~23 GB of RAM
  [ok] size: IQ1_M
  [ok] context: 65536 tokens
  [ok] KV cache: 8-bit
  [ok] images: off

  EXPERIMENTAL - speed projection: a small control vector applied while the model runs (layers 4-44).
  It changes how the model answers: its package describes it as a refusal-direction projection (the
  model declines far fewer requests). Off unless you choose it; when on, the web app can switch it off
  per chat. Details: data/experimental-speed-projection/README.md
  [ok] experimental speed projection: off

=== Step 3: Python packages ===
  Installing numpy, jinja2, regex, pyyaml, tqdm, requests, cmake, ninja, pillow, psutil ...
  > C:\Dev\Strata\.venv\Scripts\python.exe -m pip install --quiet --disable-pip-version-check numpy==2.5.3; python_version >= "3.12" numpy==2.4.6; python_version == "3.11" numpy==2.2.6; python_version < "3.11" jinja2==3.1.6 regex==2026.9.10 pyyaml==6.0.3 tqdm==4.70.1 requests==2.34.2 cmake==4.4.3 ninja==1.13.2 pillow==12.3.0 psutil==7.2.2 markupsafe==3.0.3 certifi==2026.7.22 charset-normalizer==3.5.1 idna==3.20 urllib3==2.8.0 colorama==0.4.6; sys_platform == "win32"
  [ok] numpy, jinja2, regex, pyyaml, tqdm, requests, cmake, ninja, pillow, psutil installed

=== Step 4: the Strata engine ===

  llama.cpp source:   0.01 / 0.04 GB (21%)
  [ok] llama.cpp source downloaded
  [ok] llama.cpp 3cf0325 (gguf-py, ggml, mtmd)
  Downloading the ready-made Strata engine for AMD GPUs (with the ROCm libraries it uses) ...

  Strata AMD engine:   0.01 / 0.60 GB (1%)
  [ok] Strata AMD engine downloaded
  [ok] ready-made AMD engine 0.1.38 for gfx1100, gfx1101, gfx1102, gfx1200, gfx1201, gfx1030 (ROCm 10.2.0a20260930)
  [ok] engine: C:\Dev\Strata\engine\strata.exe

=== Step 5: downloading Qwen3.8-Flash-Next Coder IQ1_M ===
  The model files go in C:\Dev\Strata-data\models\coder-IQ1_M
  Files you already have: put them here with their original names (Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf, Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf), or use --gguf-dir <their folder>.

  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   0.01 / 29.61 GB (0%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   0.35 / 29.61 GB (1%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   0.65 / 29.61 GB (2%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   1.06 / 29.61 GB (4%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   1.44 / 29.61 GB (5%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   1.75 / 29.61 GB (6%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   2.09 / 29.61 GB (7%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   2.49 / 29.61 GB (8%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   2.88 / 29.61 GB (10%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   3.25 / 29.61 GB (11%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   3.62 / 29.61 GB (12%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   4.06 / 29.61 GB (14%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   4.39 / 29.61 GB (15%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   4.80 / 29.61 GB (16%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   5.16 / 29.61 GB (17%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   5.54 / 29.61 GB (19%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   5.83 / 29.61 GB (20%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   6.23 / 29.61 GB (21%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   6.52 / 29.61 GB (22%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   6.82 / 29.61 GB (23%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   7.14 / 29.61 GB (24%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   7.47 / 29.61 GB (25%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   7.86 / 29.61 GB (27%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   8.21 / 29.61 GB (28%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   8.54 / 29.61 GB (29%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   8.93 / 29.61 GB (30%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   9.30 / 29.61 GB (31%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:   9.64 / 29.61 GB (33%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  10.01 / 29.61 GB (34%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  10.37 / 29.61 GB (35%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  10.75 / 29.61 GB (36%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  11.13 / 29.61 GB (38%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  11.48 / 29.61 GB (39%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  11.84 / 29.61 GB (40%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  12.19 / 29.61 GB (41%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  12.50 / 29.61 GB (42%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  12.85 / 29.61 GB (43%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  13.15 / 29.61 GB (44%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  13.53 / 29.61 GB (46%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  13.88 / 29.61 GB (47%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  14.24 / 29.61 GB (48%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  14.54 / 29.61 GB (49%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  14.88 / 29.61 GB (50%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  15.24 / 29.61 GB (51%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  15.62 / 29.61 GB (53%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  15.93 / 29.61 GB (54%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  16.28 / 29.61 GB (55%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  16.60 / 29.61 GB (56%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  16.93 / 29.61 GB (57%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  17.25 / 29.61 GB (58%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  17.58 / 29.61 GB (59%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  17.96 / 29.61 GB (61%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  18.32 / 29.61 GB (62%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  18.63 / 29.61 GB (63%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  18.98 / 29.61 GB (64%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  19.31 / 29.61 GB (65%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  19.75 / 29.61 GB (67%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  20.07 / 29.61 GB (68%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  20.48 / 29.61 GB (69%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  20.86 / 29.61 GB (70%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  21.22 / 29.61 GB (72%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  21.62 / 29.61 GB (73%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  21.94 / 29.61 GB (74%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  22.29 / 29.61 GB (75%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  22.62 / 29.61 GB (76%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  22.99 / 29.61 GB (78%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  23.37 / 29.61 GB (79%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  23.71 / 29.61 GB (80%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  24.07 / 29.61 GB (81%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  24.43 / 29.61 GB (83%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  24.83 / 29.61 GB (84%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  25.22 / 29.61 GB (85%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  25.52 / 29.61 GB (86%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  25.94 / 29.61 GB (88%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  26.21 / 29.61 GB (89%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  26.65 / 29.61 GB (90%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  27.04 / 29.61 GB (91%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  27.37 / 29.61 GB (92%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  27.75 / 29.61 GB (94%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  28.11 / 29.61 GB (95%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  28.53 / 29.61 GB (96%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  28.81 / 29.61 GB (97%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  28.96 / 29.61 GB (98%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf:  29.34 / 29.61 GB (99%)
  [ok] Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf downloaded

  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   0.01 / 28.80 GB (0%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   0.39 / 28.80 GB (1%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   0.83 / 28.80 GB (3%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   1.31 / 28.80 GB (5%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   1.79 / 28.80 GB (6%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   2.23 / 28.80 GB (8%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   2.68 / 28.80 GB (9%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   3.11 / 28.80 GB (11%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   3.54 / 28.80 GB (12%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   3.99 / 28.80 GB (14%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   4.45 / 28.80 GB (15%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   4.88 / 28.80 GB (17%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   5.27 / 28.80 GB (18%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   5.74 / 28.80 GB (20%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   6.19 / 28.80 GB (21%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   6.64 / 28.80 GB (23%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   7.10 / 28.80 GB (25%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   7.55 / 28.80 GB (26%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   8.03 / 28.80 GB (28%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   8.15 / 28.80 GB (28%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   8.55 / 28.80 GB (30%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   9.03 / 28.80 GB (31%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   9.44 / 28.80 GB (33%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:   9.89 / 28.80 GB (34%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  10.37 / 28.80 GB (36%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  10.85 / 28.80 GB (38%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  11.32 / 28.80 GB (39%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  11.72 / 28.80 GB (41%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  12.16 / 28.80 GB (42%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  12.63 / 28.80 GB (44%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  13.09 / 28.80 GB (45%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  13.54 / 28.80 GB (47%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  14.02 / 28.80 GB (49%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  14.47 / 28.80 GB (50%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  14.86 / 28.80 GB (52%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  15.34 / 28.80 GB (53%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  15.82 / 28.80 GB (55%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  16.25 / 28.80 GB (56%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  16.73 / 28.80 GB (58%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  17.21 / 28.80 GB (60%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  17.65 / 28.80 GB (61%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  18.13 / 28.80 GB (63%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  18.61 / 28.80 GB (65%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  19.06 / 28.80 GB (66%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  19.54 / 28.80 GB (68%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  19.99 / 28.80 GB (69%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  20.40 / 28.80 GB (71%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  20.88 / 28.80 GB (72%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  21.36 / 28.80 GB (74%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  21.81 / 28.80 GB (76%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  22.26 / 28.80 GB (77%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  22.73 / 28.80 GB (79%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  23.19 / 28.80 GB (81%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  23.62 / 28.80 GB (82%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  24.08 / 28.80 GB (84%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  24.40 / 28.80 GB (85%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  24.87 / 28.80 GB (86%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  25.19 / 28.80 GB (87%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  25.58 / 28.80 GB (89%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  26.02 / 28.80 GB (90%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  26.48 / 28.80 GB (92%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  26.95 / 28.80 GB (94%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  27.41 / 28.80 GB (95%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  27.88 / 28.80 GB (97%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  27.93 / 28.80 GB (97%)
  Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf:  28.35 / 28.80 GB (98%)
  [ok] Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf downloaded
  [ok] model files present

=== Step 6: preparing the model for Strata ===
  > C:\Dev\Strata\.venv\Scripts\python.exe C:\Dev\Strata\tools\iq_pack.py --gguf C:\Dev\Strata-data\models\coder-IQ1_M\Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf --out C:\Dev\Strata-data\packs\coder-iq1_m
model shards: Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf, Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00002-of-00002.gguf
index.txt: 1079 tensors, 302 served natively, 0 in extra.bin, arena 1.37 GiB
tokenizer/: vocab 248320, merges 247587, pre qwen35, specials {'tokenizer.ggml.eos_token_id': 248046, 'tokenizer.ggml.padding_token_id': 248044, 'tokenizer.ggml.bos_token_id': 248044}
  [ok] model prepared: C:\Dev\Strata-data\packs\coder-iq1_m
  The MTP draft layer (speculative decoding, ~2x faster output) comes from the original Qwen checkpoint:
  only its ~5 GB of MTP tensors are downloaded.
  > C:\Dev\Strata\.venv\Scripts\python.exe C:\Dev\Strata\tools\mtp_fetch.py fetch --out C:\Dev\Strata-data\mtp
# MTP block in the BF16 checkpoint

31 tensors, 5.214 GB, in 28 shards.

| tensor | dtype | shape | MB |
|---|---|---|---:|
| `mtp.fc_embedding.weight` | BF16 | 2560x2560 | 13.1 |
| `mtp.fc_hidden.weight` | BF16 | 2560x2560 | 13.1 |
| `mtp.hyper_connection_mixer.hc_norm.weight` | BF16 | 10240 | 0.0 |
| `mtp.hyper_connection_mixer.input_mix_weight_down.weight` | BF16 | 320x10240 | 6.6 |
| `mtp.hyper_connection_mixer.input_mix_weight_up.weight` | BF16 | 10240x320 | 6.6 |
| `mtp.layers.0.attn_hyper_connection.block_inject_weight.weight` | BF16 | 4x10240 | 0.1 |
| `mtp.layers.0.attn_hyper_connection.hc_norm.weight` | BF16 | 10240 | 0.0 |
| `mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight` | BF16 | 320x10240 | 6.6 |
| `mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight` | BF16 | 10240x320 | 6.6 |
| `mtp.layers.0.mlp.experts.down_proj` | BF16 | 512x2560x640 | 1677.7 |
| `mtp.layers.0.mlp.experts.gate_up_proj` | BF16 | 512x1280x2560 | 3355.4 |
| `mtp.layers.0.mlp.gate.weight` | BF16 | 512x2560 | 2.6 |
| `mtp.layers.0.mlp.shared_expert.down_proj.weight` | BF16 | 2560x640 | 3.3 |
| `mtp.layers.0.mlp.shared_expert.gate_proj.weight` | BF16 | 640x2560 | 3.3 |
| `mtp.layers.0.mlp.shared_expert.up_proj.weight` | BF16 | 640x2560 | 3.3 |
| `mtp.layers.0.mlp.shared_expert_gate.weight` | BF16 | 1x2560 | 0.0 |
| `mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight` | BF16 | 4x10240 | 0.1 |
| `mtp.layers.0.mlp_hyper_connection.hc_norm.weight` | BF16 | 10240 | 0.0 |
| `mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight` | BF16 | 320x10240 | 6.6 |
| `mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight` | BF16 | 10240x320 | 6.6 |
| `mtp.layers.0.self_attn.indexer.index_qk_proj.weight` | BF16 | 640x2560 | 3.3 |
| `mtp.layers.0.self_attn.indexer.k_layernorm.weight` | BF16 | 128 | 0.0 |
| `mtp.layers.0.self_attn.indexer.q_layernorm.weight` | BF16 | 128 | 0.0 |
| `mtp.layers.0.self_attn.k_norm.weight` | BF16 | 256 | 0.0 |
| `mtp.layers.0.self_attn.k_proj.weight` | BF16 | 512x2560 | 2.6 |
| `mtp.layers.0.self_attn.o_proj.weight` | BF16 | 2560x6144 | 31.5 |
| `mtp.layers.0.self_attn.q_norm.weight` | BF16 | 256 | 0.0 |
| `mtp.layers.0.self_attn.q_proj.weight` | BF16 | 12288x2560 | 62.9 |
| `mtp.layers.0.self_attn.v_proj.weight` | BF16 | 512x2560 | 2.6 |
| `mtp.pre_fc_norm_embedding.weight` | BF16 | 2560 | 0.0 |
| `mtp.pre_fc_norm_hidden.weight` | BF16 | 10240 | 0.0 |

mtp.fc_embedding.weight 100%
mtp.fc_hidden.weight 100%
mtp.hyper_connection_mixer.hc_norm.weight 100%
mtp.hyper_connection_mixer.input_mix_weight_down.weight 100%
mtp.hyper_connection_mixer.input_mix_weight_up.weight 100%
mtp.layers.0.attn_hyper_connection.block_inject_weight.weight 100%
mtp.layers.0.attn_hyper_connection.hc_norm.weight 100%
mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight 100%
mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight 100%
mtp.layers.0.mlp.experts.down_proj 4%
mtp.layers.0.mlp.experts.down_proj 8%
mtp.layers.0.mlp.experts.down_proj 12%
mtp.layers.0.mlp.experts.down_proj 16%
mtp.layers.0.mlp.experts.down_proj 20%
mtp.layers.0.mlp.experts.down_proj 24%
mtp.layers.0.mlp.experts.down_proj 28%
mtp.layers.0.mlp.experts.down_proj 32%
mtp.layers.0.mlp.experts.down_proj 36%
mtp.layers.0.mlp.experts.down_proj 40%
mtp.layers.0.mlp.experts.down_proj 44%
mtp.layers.0.mlp.experts.down_proj 48%
mtp.layers.0.mlp.experts.down_proj 52%
mtp.layers.0.mlp.experts.down_proj 56%
mtp.layers.0.mlp.experts.down_proj 60%
mtp.layers.0.mlp.experts.down_proj 64%
mtp.layers.0.mlp.experts.down_proj 68%
mtp.layers.0.mlp.experts.down_proj 72%
mtp.layers.0.mlp.experts.down_proj 76%
mtp.layers.0.mlp.experts.down_proj 80%
mtp.layers.0.mlp.experts.down_proj 84%
mtp.layers.0.mlp.experts.down_proj 88%
mtp.layers.0.mlp.experts.down_proj 92%
mtp.layers.0.mlp.experts.down_proj 96%
mtp.layers.0.mlp.experts.down_proj 100%
mtp.layers.0.mlp.experts.gate_up_proj 2%
mtp.layers.0.mlp.experts.gate_up_proj 4%
mtp.layers.0.mlp.experts.gate_up_proj 6%
mtp.layers.0.mlp.experts.gate_up_proj 8%
mtp.layers.0.mlp.experts.gate_up_proj 10%
mtp.layers.0.mlp.experts.gate_up_proj 12%
mtp.layers.0.mlp.experts.gate_up_proj 14%
mtp.layers.0.mlp.experts.gate_up_proj 16%
mtp.layers.0.mlp.experts.gate_up_proj 18%
mtp.layers.0.mlp.experts.gate_up_proj 20%
mtp.layers.0.mlp.experts.gate_up_proj 22%
mtp.layers.0.mlp.experts.gate_up_proj 24%
mtp.layers.0.mlp.experts.gate_up_proj 26%
mtp.layers.0.mlp.experts.gate_up_proj 28%
mtp.layers.0.mlp.experts.gate_up_proj 30%
mtp.layers.0.mlp.experts.gate_up_proj 32%
mtp.layers.0.mlp.experts.gate_up_proj 34%
mtp.layers.0.mlp.experts.gate_up_proj 36%
mtp.layers.0.mlp.experts.gate_up_proj 38%
mtp.layers.0.mlp.experts.gate_up_proj 40%
mtp.layers.0.mlp.experts.gate_up_proj 42%
mtp.layers.0.mlp.experts.gate_up_proj 44%
mtp.layers.0.mlp.experts.gate_up_proj 46%
mtp.layers.0.mlp.experts.gate_up_proj 48%
mtp.layers.0.mlp.experts.gate_up_proj 50%
mtp.layers.0.mlp.experts.gate_up_proj 52%
mtp.layers.0.mlp.experts.gate_up_proj 54%
mtp.layers.0.mlp.experts.gate_up_proj 56%
mtp.layers.0.mlp.experts.gate_up_proj 58%
mtp.layers.0.mlp.experts.gate_up_proj 60%
mtp.layers.0.mlp.experts.gate_up_proj 62%
mtp.layers.0.mlp.experts.gate_up_proj 64%
mtp.layers.0.mlp.experts.gate_up_proj 66%
mtp.layers.0.mlp.experts.gate_up_proj 68%
mtp.layers.0.mlp.experts.gate_up_proj 70%
mtp.layers.0.mlp.experts.gate_up_proj 72%
mtp.layers.0.mlp.experts.gate_up_proj 74%
mtp.layers.0.mlp.experts.gate_up_proj 76%
mtp.layers.0.mlp.experts.gate_up_proj 78%
mtp.layers.0.mlp.experts.gate_up_proj 80%
mtp.layers.0.mlp.experts.gate_up_proj 82%
mtp.layers.0.mlp.experts.gate_up_proj 84%
mtp.layers.0.mlp.experts.gate_up_proj 86%
mtp.layers.0.mlp.experts.gate_up_proj 88%
mtp.layers.0.mlp.experts.gate_up_proj 90%
mtp.layers.0.mlp.experts.gate_up_proj 92%
mtp.layers.0.mlp.experts.gate_up_proj 94%
mtp.layers.0.mlp.experts.gate_up_proj 96%
mtp.layers.0.mlp.experts.gate_up_proj 98%
mtp.layers.0.mlp.experts.gate_up_proj 100%
mtp.layers.0.mlp.gate.weight 100%
mtp.layers.0.mlp.shared_expert.down_proj.weight 100%
mtp.layers.0.mlp.shared_expert.gate_proj.weight 100%
mtp.layers.0.mlp.shared_expert.up_proj.weight 100%
mtp.layers.0.mlp.shared_expert_gate.weight 100%
mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight 100%
mtp.layers.0.mlp_hyper_connection.hc_norm.weight 100%
mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight 100%
mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight 100%
mtp.layers.0.self_attn.indexer.index_qk_proj.weight 100%
mtp.layers.0.self_attn.indexer.k_layernorm.weight 100%
mtp.layers.0.self_attn.indexer.q_layernorm.weight 100%
mtp.layers.0.self_attn.k_norm.weight 100%
mtp.layers.0.self_attn.k_proj.weight 100%
mtp.layers.0.self_attn.o_proj.weight 100%
mtp.layers.0.self_attn.q_norm.weight 100%
mtp.layers.0.self_attn.q_proj.weight 100%
mtp.layers.0.self_attn.v_proj.weight 100%
mtp.pre_fc_norm_embedding.weight 100%
mtp.pre_fc_norm_hidden.weight 100%
  > C:\Dev\Strata\.venv\Scripts\python.exe C:\Dev\Strata\tools\mtp_pack.py --src C:\Dev\Strata-data\mtp --experts q2_0 --out C:\Dev\Strata-data\mtp\mtp-q2_0.gguf
mtp.fc_embedding.weight: BF16 13.1 MB
mtp.fc_hidden.weight: BF16 13.1 MB
mtp.hyper_connection_mixer.hc_norm.weight: F32 0.0 MB
mtp.hyper_connection_mixer.input_mix_weight_down.weight: BF16 6.6 MB
mtp.hyper_connection_mixer.input_mix_weight_up.weight: BF16 6.6 MB
mtp.layers.0.attn_hyper_connection.block_inject_weight.weight: BF16 0.1 MB
mtp.layers.0.attn_hyper_connection.hc_norm.weight: F32 0.0 MB
mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight: BF16 6.6 MB
mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight: BF16 6.6 MB
mtp.layers.0.mlp.experts.down_proj: q2_0 235.9 MB
mtp.layers.0.mlp.experts.gate_up_proj: q2_0 471.9 MB
mtp.layers.0.mlp.gate.weight: BF16 2.6 MB
mtp.layers.0.mlp.shared_expert.down_proj.weight: BF16 3.3 MB
mtp.layers.0.mlp.shared_expert.gate_proj.weight: BF16 3.3 MB
mtp.layers.0.mlp.shared_expert.up_proj.weight: BF16 3.3 MB
mtp.layers.0.mlp.shared_expert_gate.weight: BF16 0.0 MB
mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight: BF16 0.1 MB
mtp.layers.0.mlp_hyper_connection.hc_norm.weight: F32 0.0 MB
mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight: BF16 6.6 MB
mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight: BF16 6.6 MB
mtp.layers.0.self_attn.indexer.index_qk_proj.weight: BF16 3.3 MB
mtp.layers.0.self_attn.indexer.k_layernorm.weight: F32 0.0 MB
mtp.layers.0.self_attn.indexer.q_layernorm.weight: F32 0.0 MB
mtp.layers.0.self_attn.k_norm.weight: F32 0.0 MB
mtp.layers.0.self_attn.k_proj.weight: BF16 2.6 MB
mtp.layers.0.self_attn.o_proj.weight: BF16 31.5 MB
mtp.layers.0.self_attn.q_norm.weight: F32 0.0 MB
mtp.layers.0.self_attn.q_proj.weight: BF16 62.9 MB
mtp.layers.0.self_attn.v_proj.weight: BF16 2.6 MB
mtp.pre_fc_norm_embedding.weight: F32 0.0 MB
mtp.pre_fc_norm_hidden.weight: F32 0.0 MB
wrote C:\Dev\Strata-data\mtp\mtp-q2_0.gguf: 0.889 GB of tensor data
  > C:\Dev\Strata\.venv\Scripts\python.exe C:\Dev\Strata\tools\mtp_rt.py --gguf C:\Dev\Strata-data\mtp\mtp-q2_0.gguf --out C:\Dev\Strata-data\mtp\rt
experts.bin 707788800 B, dense.bin 116099072 B, 29 tensors -> C:\Dev\Strata-data\mtp\rt
  fc_embedding.weight q8_0 2560 2560 0 6963200
  fc_hidden.weight q8_0 2560 2560 6963200 6963200
  hyper_connection_mixer.hc_norm.weight f32 1 10240 13926400 40960
  hyper_connection_mixer.input_mix_weight_down.weight bf16 320 10240 13967360 6553600
  hyper_connection_mixer.input_mix_weight_up.weight bf16 10240 320 20520960 6553600
  attn_hyper_connection.block_inject_weight.weight bf16 4 10240 27074560 81920
  attn_hyper_connection.hc_norm.weight f32 1 10240 27156480 40960
  attn_hyper_connection.input_mix_weight_down.weight bf16 320 10240 27197440 6553600
  attn_hyper_connection.input_mix_weight_up.weight bf16 10240 320 33751040 6553600
  mlp.gate.weight bf16 512 2560 40304640 2621440
  mlp.shared_expert.down_proj.weight q8_0 2560 640 42926080 1740800
  mlp.shared_expert.gate_proj.weight q8_0 640 2560 44666880 1740800
  mlp.shared_expert.up_proj.weight q8_0 640 2560 46407680 1740800
  mlp.shared_expert_gate.weight bf16 1 2560 48148480 5120
  mlp_hyper_connection.block_inject_weight.weight bf16 4 10240 48153600 81920
  mlp_hyper_connection.hc_norm.weight f32 1 10240 48235520 40960
  mlp_hyper_connection.input_mix_weight_down.weight bf16 320 10240 48276480 6553600
  mlp_hyper_connection.input_mix_weight_up.weight bf16 10240 320 54830080 6553600
  self_attn.indexer.index_qk_proj.weight q8_0 640 2560 61383680 1740800
  self_attn.indexer.k_layernorm.weight f32 1 128 63124480 512
  self_attn.indexer.q_layernorm.weight f32 1 128 63124992 512
  self_attn.k_norm.weight f32 1 256 63125504 1024
  self_attn.k_proj.weight q8_0 512 2560 63126528 1392640
  self_attn.o_proj.weight q8_0 2560 6144 64519168 16711680
  self_attn.q_norm.weight f32 1 256 81230848 1024
  self_attn.q_proj.weight q8_0 12288 2560 81231872 33423360
  self_attn.v_proj.weight q8_0 512 2560 114655232 1392640
  pre_fc_norm_embedding.weight f32 1 2560 116047872 10240
  pre_fc_norm_hidden.weight f32 1 10240 116058112 40960
  [ok] MTP draft layer: C:\Dev\Strata-data\mtp\rt

=== Step 7: writing the start script ===
  [ok] KV streaming on: the context's KV cache lives in RAM (0.9 GB), more experts fit in VRAM
  [!]  no hipBLASLt tuning table for gfx1030 with hipBLASLt 100500: the prompt's dense matrix products use plain hipBLAS (tools/hip/tune_hipblaslt makes a table: docs/AMD_HIP.md, Tuning table)
  [ok] start script: run-coder-iq1_m.bat

All set.
  API (OpenAI):     http://127.0.0.1:8080/v1   (any API key; model name: anything)
  API (Anthropic):  http://127.0.0.1:8080/v1/messages
  Next time:        just run START-HERE.bat (or run-coder-iq1_m.bat) - it starts right away
