Skip to content
Run LLM Locally

Llama 4 Scout 17B-16E Instruct on the RTX PRO 6000 Blackwell

With 96 GB of VRAM, the RTX PRO 6000 Blackwell runs Llama 4 Scout 17B-16E Instruct at Q4_K_M entirely on the GPU with an 8K context (about 68.6 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Llama 4 Scout 17B-16E Instruct

Q4_K_M · 8K context

Excellent

The model needs about 68.6 GB and fits in the 93.1 GB available, with 24.5 GB to spare.

Your hardware
RTX PRO 6000 Blackwell 96 GB · 64 GB RAM
Estimated memory
~68.6 GB estimate
VRAM (usable memory)
93.1 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
71–106 tok/s estimate
Largest context in fast memory
506K tokens
Confidence: low

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

Memory breakdown

~68.6 GB (66.9 GB–70.3 GB) needed · estimate

Fits entirely in VRAM · 24.5 GB left

  • Model weights62.9 GB
  • KV cache1.5 GB
  • Runtime overhead0.9 GB
  • Safety margin3.3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · 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 RTX PRO 6000 Blackwell

Llama 4 Scout 17B-16E Instruct on RTX PRO 6000 Blackwell + 64 GB RAM · 8K context
Llama 4 Scout 17B-16E Instruct Q8_08K~113 GB · 5.5–10 tok/s estimateCPU/GPU offload
Llama 4 Scout 17B-16E Instruct Q6_K8K~89 GB · 59–86 tok/s estimateCompatible
Llama 4 Scout 17B-16E Instruct Q5_K_M8K~77.4 GB · 65–96 tok/s estimateExcellent
Llama 4 Scout 17B-16E Instruct Q4_K_M8K~68.6 GB · 71–106 tok/s estimateExcellent
Llama 4 Scout 17B-16E Instruct IQ4_XS8K~61.1 GB · 76–115 tok/s estimateExcellent
Llama 4 Scout 17B-16E Instruct Q3_K_M8K~55.7 GB · 81–123 tok/s estimateExcellent

Alternatives

GPUs that run Llama 4 Scout 17B-16E Instruct 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 Llama 4 Scout 17B-16E 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 RTX PRO 6000 Blackwell run Llama 4 Scout 17B-16E Instruct?
    The model needs about 68.6 GB and fits in the 93.1 GB available, with 24.5 GB to spare.
    Which quantization should I use on the RTX PRO 6000 Blackwell?
    Q6_K is the highest-precision quantization that fits entirely in VRAM at 8K context. ~89 GB / 93.1 GB.
    What is the largest context on the RTX PRO 6000 Blackwell?
    At Q4_K_M, about 506K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
    How fast is Llama 4 Scout 17B-16E Instruct (RTX PRO 6000 Blackwell)?
    We estimate 71–106 tok/s (estimate, confidence low). Based on: memory bandwidth (1,792 GB/s) and model size.