Skip to content
Run LLM Locally

Mixtral 8x7B Instruct on the Radeon PRO W7900

With 48 GB of VRAM, the Radeon PRO W7900 runs Mixtral 8x7B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 27.6 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Mixtral 8x7B Instruct

Q4_K_M · 8K context

Excellent

The model needs about 27.6 GB and fits in the 46.6 GB available, with 19 GB to spare.

Your hardware
Radeon PRO W7900 48 GB · 64 GB RAM
Estimated memory
~27.6 GB estimate
VRAM (usable memory)
46.6 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
45–70 tok/s estimate
Largest context in fast memory
32K tokens
Confidence: low

Based on: memory bandwidth (864 GB/s) and model size

Memory breakdown

~27.6 GB (26.8 GB–28.4 GB) needed · estimate

Fits entirely in VRAM · 19 GB left

  • Model weights24.6 GB
  • KV cache1 GB
  • Runtime overhead0.6 GB
  • Safety margin1.3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (ROCm) · flash attention on · weights = real file size

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet
  • mixture-of-experts: speed depends on expert routing

Other quantizations on the Radeon PRO W7900

Mixtral 8x7B Instruct on Radeon PRO W7900 + 64 GB RAM · 8K context
Mixtral 8x7B Instruct Q8_08K~50.2 GB · 11–20 tok/s estimateCPU/GPU offload
Mixtral 8x7B Instruct Q6_K8K~39.2 GB · 34–52 tok/s estimateExcellent
Mixtral 8x7B Instruct Q5_K_M8K~33.2 GB · 39–60 tok/s estimateExcellent
Mixtral 8x7B Instruct Q4_K_M8K~27.6 GB · 45–70 tok/s estimateExcellent
Mixtral 8x7B Instruct IQ4_XS8K~27.2 GB · 46–71 tok/s estimateExcellent
Mixtral 8x7B Instruct Q3_K_M8K~21.6 GB · 54–85 tok/s estimateExcellent

Alternatives

GPUs that run Mixtral 8x7B Instruct Q4_K_M entirely in VRAM

Other models that fit the Radeon PRO W7900

Where to buy a Radeon PRO W7900

Prices and links follow the market you choose.

Radeon PRO W7900

48 GB GDDR6 ECC · 864 GB/s · 295 W

ExcellentRuns Mixtral 8x7B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the Radeon PRO W7900 run Mixtral 8x7B Instruct?
The model needs about 27.6 GB and fits in the 46.6 GB available, with 19 GB to spare.
Which quantization should I use on the Radeon PRO W7900?
Q6_K is the highest-precision quantization that fits entirely in VRAM at 8K context. ~39.2 GB / 46.6 GB.
What is the largest context on the Radeon PRO W7900?
At Q4_K_M, about 32K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Mixtral 8x7B Instruct (Radeon PRO W7900)?
We estimate 45–70 tok/s (estimate, confidence low). Based on: memory bandwidth (864 GB/s) and model size.