mirror of
https://github.com/Niko1221/Strata.git
synced 2026-11-09 03:59:45 -10:00
READMEs: DeepSeek on Mac reads pictures too (dropped 'text only'); the 7 translations now name Strix Halo and the Mac like the English page; MAC.md and MODELS.md say the same in plain words
This commit is contained in:
Niko1221 committed
1 parent
3d26434f21
commit
321794636c
10 files changed
+10
-10
No files matched your search
+1
-1
@@ -63,7 +63,7 @@ In der **Desktop-App** und im **Terminal**. Was nicht in den Arbeitsspeicher pas
|
||||
| 2.00 bpw | 257 GB | etwa 265 GB |
|
||||
| 2.25 bpw | 274 GB | etwa 280 GB |
|
||||
|
||||
Läuft auf NVIDIA RTX 30, 40 und 50 (Windows und Linux) und auf AMD Radeon AI PRO R9700 (Linux). Das Setup lädt die Dateien und die DeepSeek-Engine herunter und startet dann das Modell.
|
||||
Läuft auf NVIDIA RTX 30, 40 und 50 (Windows und Linux), AMD Radeon AI PRO R9700 (Linux), AMD Ryzen AI Max — Strix Halo (Windows) und Apple-Silicon-Macs mit 64 GB oder mehr ([Mac](docs/DEEPSEEK_MAC.md)). Das Setup lädt die Dateien und die DeepSeek-Engine herunter und startet dann das Modell.
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -63,7 +63,7 @@ En la **aplicación de escritorio** y en el **Terminal**. Lo que no cabe en la m
|
||||
| 2.00 bpw | 257 GB | unos 265 GB |
|
||||
| 2.25 bpw | 274 GB | unos 280 GB |
|
||||
|
||||
Funciona en NVIDIA RTX 30, 40 y 50 (Windows y Linux) y en AMD Radeon AI PRO R9700 (Linux). La instalación descarga los archivos y el motor de DeepSeek, y después inicia el modelo.
|
||||
Funciona en NVIDIA RTX 30, 40 y 50 (Windows y Linux), AMD Radeon AI PRO R9700 (Linux), AMD Ryzen AI Max — Strix Halo (Windows) y Macs con Apple Silicon de 64 GB o más ([Mac](docs/DEEPSEEK_MAC.md)). La instalación descarga los archivos y el motor de DeepSeek, y después inicia el modelo.
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -63,7 +63,7 @@ Dans l'**application de bureau** et dans le **Terminal**. Ce qui ne tient pas en
|
||||
| 2.00 bpw | 257 GB | environ 265 GB |
|
||||
| 2.25 bpw | 274 GB | environ 280 GB |
|
||||
|
||||
Fonctionne sur les NVIDIA RTX 30, 40 et 50 (Windows et Linux) et sur l'AMD Radeon AI PRO R9700 (Linux). L'installation télécharge les fichiers et le moteur DeepSeek, puis démarre le modèle.
|
||||
Fonctionne sur les NVIDIA RTX 30, 40 et 50 (Windows et Linux), l'AMD Radeon AI PRO R9700 (Linux), l'AMD Ryzen AI Max — Strix Halo (Windows) et les Mac Apple Silicon avec 64 Go ou plus ([Mac](docs/DEEPSEEK_MAC.md)). L'installation télécharge les fichiers et le moteur DeepSeek, puis démarre le modèle.
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -63,7 +63,7 @@
|
||||
| 2.00 bpw | 257 GB | 約265 GB |
|
||||
| 2.25 bpw | 274 GB | 約280 GB |
|
||||
|
||||
NVIDIA RTX 30・40・50 シリーズ（Windows と Linux）と、AMD Radeon AI PRO R9700（Linux）で動きます。セットアップがファイルと DeepSeek エンジンをダウンロードし、モデルを起動します。
|
||||
NVIDIA RTX 30・40・50 シリーズ（Windows と Linux）、AMD Radeon AI PRO R9700（Linux）、AMD Ryzen AI Max — Strix Halo（Windows）、メモリ 64 GB 以上の Apple シリコン搭載 Mac（[Mac](docs/DEEPSEEK_MAC.md)）で動きます。セットアップがファイルと DeepSeek エンジンをダウンロードし、モデルを起動します。
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
@@ -66,7 +66,7 @@ disk space.
|
||||
| ISTA-DAS Coder (half of the experts removed) | 191 GB | about 197 GB |
|
||||
|
||||
Runs on NVIDIA RTX 30, 40 and 50 series (Windows and Linux), AMD Radeon AI PRO R9700 (Linux), AMD Ryzen AI Max — Strix Halo
|
||||
(Windows), and Apple Silicon Macs with 64 GB or more, text only ([Mac](docs/DEEPSEEK_MAC.md)). Setup downloads the files and the DeepSeek engine, then starts the model.
|
||||
(Windows), and Apple Silicon Macs with 64 GB or more ([Mac](docs/DEEPSEEK_MAC.md)). Setup downloads the files and the DeepSeek engine, then starts the model.
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -65,7 +65,7 @@ dużo wolnego miejsca na dysku.
|
||||
| 2.25 bpw | 274 GB | około 280 GB |
|
||||
|
||||
Działa na kartach NVIDIA RTX serii 30, 40 i 50 (Windows i Linux), AMD Radeon AI PRO R9700 (Linux) oraz AMD Ryzen AI Max — Strix Halo
|
||||
(Windows). Instalacja pobiera pliki i silnik DeepSeek, a potem uruchamia model.
|
||||
(Windows) oraz na komputerach Mac z Apple Silicon i co najmniej 64 GB pamięci ([Mac](docs/DEEPSEEK_MAC.md)). Instalacja pobiera pliki i silnik DeepSeek, a potem uruchamia model.
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -63,7 +63,7 @@ No **aplicativo de desktop** e no **Terminal**. O que não cabe na memória é l
|
||||
| 2.00 bpw | 257 GB | cerca de 265 GB |
|
||||
| 2.25 bpw | 274 GB | cerca de 280 GB |
|
||||
|
||||
Roda em NVIDIA RTX 30, 40 e 50 (Windows e Linux) e em AMD Radeon AI PRO R9700 (Linux). A instalação baixa os arquivos e o motor do DeepSeek e depois inicia o modelo.
|
||||
Roda em NVIDIA RTX 30, 40 e 50 (Windows e Linux), AMD Radeon AI PRO R9700 (Linux), AMD Ryzen AI Max — Strix Halo (Windows) e Macs com Apple Silicon e 64 GB ou mais ([Mac](docs/DEEPSEEK_MAC.md)). A instalação baixa os arquivos e o motor do DeepSeek e depois inicia o modelo.
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -63,7 +63,7 @@
|
||||
| 2.00 bpw | 257 GB | 约265 GB |
|
||||
| 2.25 bpw | 274 GB | 约280 GB |
|
||||
|
||||
支持 NVIDIA RTX 30、40 和 50 系列（Windows 和 Linux），以及 AMD Radeon AI PRO R9700（Linux）。安装程序会下载模型文件和 DeepSeek 引擎，然后启动模型。
|
||||
支持 NVIDIA RTX 30、40 和 50 系列（Windows 和 Linux）、AMD Radeon AI PRO R9700（Linux）、AMD Ryzen AI Max — Strix Halo（Windows），以及内存 64 GB 或以上的 Apple 芯片 Mac（[Mac](docs/DEEPSEEK_MAC.md)）。安装程序会下载模型文件和 DeepSeek 引擎，然后启动模型。
|
||||
|
||||
```sh
|
||||
strata launch --family deepseek41 --model ist-das-2.00bpw --plan
|
||||
|
||||
+1
-1
@@ -3,7 +3,7 @@
|
||||
This page is for people with an Apple Silicon Mac (M1 or newer). Strata runs there on its own Metal engine: the NVIDIA kernels
|
||||
are replaced by Metal ones (`metal/`), and the host code and the server are the PC's. Intel Macs cannot run it.
|
||||
|
||||
DeepSeek V4.1-Flash runs on a Mac with 64 GB of memory or more. It reads pictures when its engine carries the Metal picture reader: [DEEPSEEK_MAC.md](DEEPSEEK_MAC.md). It has its
|
||||
DeepSeek V4.1-Flash runs on a Mac with 64 GB of memory or more, and reads pictures too: [DEEPSEEK_MAC.md](DEEPSEEK_MAC.md). It has its
|
||||
own engine, separate from the Qwen one described on this page.
|
||||
|
||||
> **On this page:** [What you need](#what-you-need) · [Install](#install) · [Defaults](#defaults-and-options) ·
|
||||
|
||||
+1
-1
@@ -72,7 +72,7 @@ you have the disk. Perplexity is measured on a fixed set of 4,995 test texts; lo
|
||||
| NVIDIA RTX 30, 40 and 50 series, 12 GB or more | Windows, Linux |
|
||||
| AMD Radeon AI PRO R9700 | Linux |
|
||||
| AMD Ryzen AI Max (Strix Halo, gfx1151, 128 GB unified; 64 GB or more shared with Windows) | Windows |
|
||||
| Apple Silicon Mac, 64 GB or more, macOS 15 or newer ([DEEPSEEK_MAC.md](DEEPSEEK_MAC.md); pictures need the engine's Metal picture reader) | macOS |
|
||||
| Apple Silicon Mac, 64 GB or more, macOS 15 or newer ([DEEPSEEK_MAC.md](DEEPSEEK_MAC.md); text and pictures) | macOS |
|
||||
|
||||
Tested on an RTX 3060 (Linux), an RTX 5070 (Windows), four R9700 cards (Linux) and a Ryzen AI Max+ 395 with 128 GB unified (Windows:
|
||||
14 to 16 tokens a second on code with the default Faster mode, 10 to 11 on chat, 78 tokens a second on a 4K prompt and 109 on
|
||||
|
||||
Reference in new issue
Block a user