Yes — with 15.0 GB to spare

Llama 4 Scout 109B-A17B at Q4_K_M fits your H100 PCIe entirely on the GPU at 8K context, at an estimated 49 tokens per second. Past 328K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 61.3 GB Llama 4 Community Released 5 Apr 2025 Vision

A 10M-token window on paper, chunked attention in practice (8K chunks on 3 of 4 layers). Needs 64 GB+ at Q4.

What hardware do I need for Llama 4 Scout 109B-A17B? →

The VRAM budget

weights 61.3 GB

Weights 61.3 GB KV cache @ 8K 1.50 GB Runtime overhead 0.6 GB Free 15.0 GB of 78.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	107.9 GB	110.0 GB	—	~2.6	−0.1% ppl	31.6 GB over
Q6_K	83.2 GB	85.3 GB	—	~9.7	−0.4% ppl	6.9 GB over
Q5_K_M	71.9 GB	74.0 GB	100K	41	−0.8% ppl	Long context
Q4_K_M	61.3 GB	63.4 GB	328K	49	−1.9% ppl	Recommended
Q3_K_M	49.6 GB	51.7 GB	577K	60	−5.4% ppl	Long context
Q2_K	42.5 GB	44.6 GB	728K	70	−15% ppl	Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (8192 tokens, 12 of 48 layers global), which is why its cache barely grows with context.

How to run it

Ollama llama.cpp LM Studio vLLM

terminal

$ ollama pull llama4:scout
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run llama4:scout

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 61.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.

03There is room to go to 328K context on this card.

See all models for this rig Compare with another model