Best local AI models for AMD Pro WX Vega M GL
4 GB HBM2. At a 4k context, 81 of the 233 models in our catalog with verified parameter counts fit fully, up to Lumina-Next / Lumina-Image 2.0 at 5B parameters.
Check your own machine against every model →The largest models that fit fully
The 30 largest of the 81 models that fit; every smaller model in the catalog fits too. Best quant means the highest quality compression whose weights and 4k context both sit inside the memory.
| Model | Parameters | Best quant that fits | Memory used at 4k |
|---|---|---|---|
| Lumina-Next / Lumina-Image 2.0 | 5B | Q4_K_M | 3.7 GB |
| CogVideoX 2B / 5B | 5B | Q4_K_M | 3.7 GB |
| DeepSeek-VL2 | 4.5B | Q5_K_M | 3.8 GB |
| DeepFloyd IF | 4.3B | Q5_K_M | 3.7 GB |
| Phi-3.5-vision | 4.2B | Q5_K_M | 3.6 GB |
| Qwen3 4B | 4B | Q6_K | 3.9 GB |
| Gemma 3 4B | 4B | Q6_K | 3.9 GB |
| Gemma 4 E4B | 4B | Q6_K | 3.9 GB |
| MiniCPM 3 4B | 4B | Q6_K | 3.9 GB |
| Danube 3 4B | 4B | Q6_K | 3.9 GB |
| Fish Speech 1.5 / OpenAudio S1 | 4B | Q6_K | 3.9 GB |
| Phi-4-mini-instruct | 3.8B | Q6_K | 3.7 GB |
| Phi-3.5 Mini | 3.8B | Q6_K | 3.7 GB |
| OmniGen / OmniGen2 | 3.8B | Q6_K | 3.7 GB |
| SD Cascade (Würstchen v3) | 3.6B | Q6_K | 3.5 GB |
| SDXL Turbo | 3.5B | Q6_K | 3.4 GB |
| SDXL Lightning | 3.5B | Q6_K | 3.4 GB |
| ACE-Step | 3.5B | Q6_K | 3.4 GB |
| MusicGen small/medium/large | 3.3B | Q6_K | 3.2 GB |
| SmolLM3 3B | 3B | Q8_0 | 3.8 GB |
| Replit Code v1.5 3B | 3B | Q8_0 | 3.8 GB |
| Kandinsky 3.1 | 3B | Q8_0 | 3.8 GB |
| Voxtral Mini / Small | 3B | Q8_0 | 3.8 GB |
| Orpheus TTS | 3B | Q8_0 | 3.8 GB |
| Higgs Audio v2 | 3B | Q8_0 | 3.8 GB |
| Allegro | 2.8B | Q8_0 | 3.6 GB |
| Open-Sora Plan | 2.7B | Q8_0 | 3.4 GB |
| LFM2 1.2B / 2.6B | 2.6B | Q8_0 | 3.3 GB |
| Playground v2.5 | 2.6B | Q8_0 | 3.3 GB |
| Stable Diffusion 3.5 Medium | 2.5B | Q8_0 | 3.2 GB |
Close, but only with CPU offload
These need more than the card holds at their smallest practical quant, so part of the model runs from system memory (figures assume 32 GB of it). They work, several times slower.
| Model | Parameters | Memory at FP8 / optimized | System RAM at 4k |
|---|---|---|---|
| Stable Diffusion XL | 3.417B | 4.1 GB needed | 6.1 GB |
| Phi-3 Mini | 3.8B | 4.4 GB needed | 6.4 GB |
| Phi-4-multimodal | 5.6B | 4.1 GB needed | 6.1 GB |
| Magicoder-S-DS 6.7B | 6.7B | 4.9 GB needed | 6.9 GB |
| Mistral 7B | 7B | 5.7 GB needed | 7.7 GB |
| Qwen2.5 0.5B / 1.5B / 3B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| OLMo 2 1B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| Falcon 3 1B / 3B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| Command R7B | 7B | 5.1 GB needed | 7.1 GB |
| OpenHermes 2.5 | 7B | 5.1 GB needed | 7.1 GB |
How to read this
The AMD Radeon Pro WX Vega M GL graphics processor features 4 GB of high bandwidth HBM2 memory. This dedicated video memory determines the size of the artificial intelligence models you can run locally. For optimal performance, the model files must fit entirely within this 4 GB limit to avoid slow processing speeds.
To fit inside the video memory, models use quantization. The quant column shows the compression level applied to each model. A Q4_K_M quant represents a medium four bit compression. A Q6_K quant offers six bit precision, while a Q8_0 quant provides eight bit precision. Higher precision quants deliver better output quality but require more memory space.
The largest models that fit completely within the 4 GB HBM2 memory include Lumina-Next or Lumina-Image 2.0 at 5B parameters using a Q4_K_M quant to consume 3.7 GB. CogVideoX 5B also fits at Q4_K_M using 3.7 GB. DeepSeek-VL2 at 4.5B parameters fits with a Q5_K_M quant using 3.8 GB. DeepFloyd IF at 4.3B parameters uses 3.7 GB at Q5_K_M, and Phi-3.5-vision at 4.2B parameters uses 3.6 GB at Q5_K_M.
Several 4B parameter models run at Q6_K precision using 3.9 GB of memory. These models include Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 or OpenAudio S1. Phi-4-mini-instruct and Phi-3.5 Mini both use 3.7 GB at Q6_K precision. For image generation, SDXL Turbo and SDXL Lightning at 3.5B parameters use 3.4 GB at Q6_K precision.
When a model exceeds the 4 GB video memory, you must use CPU offload. This process splits the model between your graphics card and your system RAM. Assuming you have 32 GB of system RAM, you can run larger models like Mistral 7B or Qwen2.5 7B. However, offloading data to system RAM slows down processing speeds significantly compared to running entirely on HBM2.
Under CPU offload, Mistral 7B requires 5.7 GB at Q4_K_M precision and uses 7.7 GB of system RAM. Qwen2.5 7B, OLMo 2 7B, Falcon 3 7B, Command R7B, and OpenHermes 2.5 each require 5.1 GB at Q4_K_M precision and use 7.1 GB of system RAM. Stable Diffusion XL requires 4.1 GB at FP8 precision and uses 6.1 GB of system RAM.
Memory calculations are based on a standard 4k context window. Running longer text conversations or larger prompts increases memory usage. If your context window expands beyond 4k tokens, the model may exceed the 4 GB limit and trigger slow system RAM offloading automatically.