Skip to content
Run LLM Locally

Mistral Small 4 119B on the RTX PRO 6000 Blackwell

With 96 GB of VRAM, the RTX PRO 6000 Blackwell runs Mistral Small 4 119B at Q4_K_M entirely on the GPU with an 8K context (about 72 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Mistral Small 4 119B

Q4_K_M · 8K context

Excellent

The model needs about 72 GB and fits in the 93.1 GB available, with 21.1 GB to spare.

Your hardware
RTX PRO 6000 Blackwell 96 GB · 64 GB RAM
Estimated memory
~72 GB estimate
VRAM (usable memory)
93.1 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
148–242 tok/s estimate
Largest context in fast memory
256K tokens
Confidence: low

Based on: memory bandwidth (1,792 GB/s) and model size

Memory breakdown

~72 GB (70.3 GB–73.8 GB) needed · estimate

Fits entirely in VRAM · 21.1 GB left

  • Model weights67.6 GB
  • KV cache0.2 GB
  • Runtime overhead0.8 GB
  • Safety margin3.4 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size · compressed MLA KV cache

EstimateData updated 40 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 RTX PRO 6000 Blackwell

Mistral Small 4 119B on RTX PRO 6000 Blackwell + 64 GB RAM · 8K context
Mistral Small 4 119B Q8_08K~125 GB · 10–20 tok/s estimateCPU/GPU offload
Mistral Small 4 119B Q6_K8K~102 GB · 30–58 tok/s estimateCPU/GPU offload
Mistral Small 4 119B Q5_K_M8K~84.1 GB · 136–218 tok/s estimateCompatible
Mistral Small 4 119B Q4_K_M8K~72 GB · 148–242 tok/s estimateExcellent
Mistral Small 4 119B IQ4_XS8K~63.4 GB · 158–262 tok/s estimateExcellent
Mistral Small 4 119B Q3_K_M8K~54.3 GB · 170–287 tok/s estimateExcellent

Alternatives

GPUs that run Mistral Small 4 119B Q4_K_M entirely in VRAM

    Other models that fit the RTX PRO 6000 Blackwell

    Where to buy a RTX PRO 6000 Blackwell

    Prices and links follow the market you choose.

    RTX PRO 6000 Blackwell Workstation Edition

    96 GB GDDR7 ECC · 1,792 GB/s · 600 W

    ExcellentRuns Mistral Small 4 119B 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 RTX PRO 6000 Blackwell run Mistral Small 4 119B?
    The model needs about 72 GB and fits in the 93.1 GB available, with 21.1 GB to spare.
    Which quantization should I use on the RTX PRO 6000 Blackwell?
    Q5_K_M is the highest-precision quantization that fits entirely in VRAM at 8K context. ~84.1 GB / 93.1 GB.
    What is the largest context on the RTX PRO 6000 Blackwell?
    At Q4_K_M, about 256K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
    How fast is Mistral Small 4 119B (RTX PRO 6000 Blackwell)?
    We estimate 148–242 tok/s (estimate, confidence low). Based on: memory bandwidth (1,792 GB/s) and model size.