Yes — with 136.1 GB to spare
Llama 3.2 3B Instruct at Q4_K_M fits your H200 SXM entirely on the GPU at 8K context, at an estimated 1610 tokens per second. There is room for its full 128K window.
Fully on GPU
8K context
Q4_K_M · 1.8 GB
Llama 3.2 Community
Released Sep 2024
The 2024 "it just runs" model for 8 GB laptops. Qwen3.5 4B does the same job better now.
The VRAM budget
weights 1.8 GB
Weights 1.8 GB
KV cache @ 8K 0.88 GB
Runtime overhead 0.6 GB
Free 136.1 GB of 139.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 6.0 GB | 7.5 GB | 128K | 486 | Reference | Long context |
| Q8_0 | 3.2 GB | 4.7 GB | 128K | 915 | −0.1% ppl | Long context |
| Q6_K | 2.5 GB | 3.9 GB | 128K | 1185 | −0.4% ppl | Long context |
| Q5_K_M | 2.1 GB | 3.6 GB | 128K | 1371 | −0.8% ppl | Long context |
| Q4_K_M | 1.8 GB | 3.3 GB | 128K | 1610 | −1.9% ppl | Recommended |
| Q3_K_M | 1.5 GB | 2.9 GB | 128K | 1989 | −5.4% ppl | Long context |
| Q2_K | 1.3 GB | 2.7 GB | 128K | 2321 | −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.
How to run it
$ ollama pull llama3.2:3b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run llama3.2:3b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 1.8 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 the model's full 128K context on this card.