Yes — with 57.4 GB to spare
Qwen3 32B at Q4_K_M fits your H100 PCIe entirely on the GPU at 8K context, at an estimated 66 tokens per second. There is room for its full 128K window.
Fully on GPU
8K context
Q4_K_M · 18.4 GB
Apache 2.0
Released Apr 2025
The classic 24 GB target, and still the strongest local translator under 70B. Qwen3.8 27B is smaller and better at everything else.
The VRAM budget
weights 18.4 GB
Weights 18.4 GB
KV cache @ 8K 2.00 GB
Runtime overhead 0.6 GB
Free 57.4 GB of 78.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 35.1 GB | 128K | 37 | −0.1% ppl | Long context |
| Q6_K | 25.0 GB | 27.6 GB | 128K | 48 | −0.4% ppl | Long context |
| Q5_K_M | 21.7 GB | 24.3 GB | 128K | 56 | −0.8% ppl | Long context |
| Q4_K_M | 18.4 GB | 21.0 GB | 128K | 66 | −1.9% ppl | Recommended |
| Q3_K_M | 14.9 GB | 17.5 GB | 128K | 81 | −5.4% ppl | Long context |
| Q2_K | 12.8 GB | 15.4 GB | 128K | 95 | −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 qwen3:32b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3:32b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 18.4 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.