▸ DEVICE UNDER TEST
AMD Radeon Pro WX Vega M GL — 4 GB VRAM.
▸ RADEON PRO WX VEGA M GL SPEC
- BRAND
- AMD
- VRAM
- 4 GB HBM2
- BANDWIDTH
- 179 GB/s
- FP16 COMPUTE
- 2.6 TFLOPS
- FP32 COMPUTE
- 2.6 TFLOPS
- STREAM PROCESSORS
- 1,280
- TDP
- 65 W
- ARCHITECTURE
- GCN 4.0
▸ AI CAPABILITY
106/ 449 models @ Q4
With 4 GB VRAM and 179 GB/s bandwidth, this GPU handles models up to 4.97B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~20 tok/s.
§ 01TOP MODELS FOR RADEON PRO WX VEGA M GL
106 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| TranslateGemma 4B | 4.97B | 3.5 GB | 32 | 5.5 |
| Qwen 3.5 4B | 4.66B | 3.3 GB | 34 | 47.4 |
| InternLM2 5B | 4.5B | 3.2 GB | 35 | 47.6 |
| Qwen3-VL 4B Instruct | 4.44B | 3.2 GB | 36 | 26.6 |
| MedGemma 1.5 4B | 4.3B | 3.1 GB | 37 | 5.5 |
| Gemma 3 4B | 4.3B | 3.1 GB | 37 | 22.8 |
| Ministral 3 3B Reasoning | 4.25B | 3.1 GB | 37 | — |
| Qwen 1.5 4B | 4B | 2.9 GB | 40 | 12.6 |
| Qwen3 4B | 4B | 2.9 GB | 40 | 40.7 |
| Qwen3-4B Instruct 2507 | 4B | 2.9 GB | 40 | 37.2 |
| Qwen3-Embedding 4B | 4B | 2.9 GB | 40 | — |
| Granite Vision 4.1 4B | 4B | 2.9 GB | 40 | — |
| Nemotron 3 Nano 4B | 3.97B | 2.9 GB | 40 | 32.0 |
| Ministral 3 3B | 3.85B | 2.8 GB | 41 | 21.4 |
| Phi-3.5 Mini 3.8B | 3.82B | 2.8 GB | 42 | 46.6 |
| phi-3-mini-4k 3.8B | 3.8B | 2.8 GB | 42 | 30.5 |
| Phi-4-mini 3.8B | 3.8B | 2.8 GB | 42 | 49.0 |
| Qwen2.5-VL-3B | 3.8B | 2.8 GB | 42 | 29.9 |
| Jina Embeddings v4 | 3.8B | 2.8 GB | 42 | — |
| Cogito 3B | 3.61B | 2.7 GB | 44 | 22.1 |