MistralMixtral 8x7B Instruct on AMD Radeon Pro W7900
Yes — AMD Radeon Pro W7900 handles Mixtral 8x7B Instruct well at Q5_K_M — 19 tok/s. Solid daily-driver performance on 48 GB VRAM.
Model Size
46.7B
Device VRAM
48 GB
Bandwidth
864 GB/s
Quantization
Q5_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Mixtral 8x7B Instruct on AMD Radeon Pro W7900 at Q5_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 19 tok/s | 509ms | ✓ Yes | Good | estimated |
Notes
Q5_K_M
AMD workstation card with the best ROCm support in this dataset; best AMD option for larger models. Q5_K_M fits in VRAM on this card. MoE models still have to load the full expert pool into memory.
About Mixtral 8x7B Instruct
Mixtral 8x7B Instruct (46.7B) is a chat, coding, reasoning, multi-purpose model. Mixture-of-Experts model: 46.7B total params but only ~12.9B active per token. Quality closer to a 13B dense model with inference speed to match. Needs more VRAM for the full weight set though.
View all Mixtral 8x7B Instruct hardware options →About AMD Radeon Pro W7900
AMD Radeon Pro W7900 has 48 GB at 864 GB/s. Street price: $3,299.
See all models AMD Radeon Pro W7900 can run →Estimate method: Estimated from m4-max-64gb compatibility patterns plus ROCm/Vulkan adjustments. Reference hardware source: github.com (2026-03-26)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.