Yes — with 134.2 GB to spare
Gemma 4 E4B at Q4_K_M fits your H200 SXM entirely on the GPU at 8K context, at an estimated 646 tokens per second. There is room for its full 128K window.
Fully on GPU
8K context
Q4_K_M · 4.5 GB
Apache 2.0
Released 2 Apr 2026
Vision
The laptop Gemma. 4.5B effective, 8B on disk; a single KV head per window layer keeps its cache tiny.
The VRAM budget
weights 4.5 GB
Weights 4.5 GB
KV cache @ 8K 0.14 GB
Runtime overhead 0.6 GB
Free 134.2 GB of 139.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 14.9 GB | 15.6 GB | 128K | 195 | Reference | Long context |
| Q8_0 | 7.9 GB | 8.7 GB | 128K | 367 | −0.1% ppl | Long context |
| Q6_K | 6.1 GB | 6.9 GB | 128K | 476 | −0.4% ppl | Long context |
| Q5_K_M | 5.3 GB | 6.0 GB | 128K | 550 | −0.8% ppl | Long context |
| Q4_K_M | 4.5 GB | 5.2 GB | 128K | 646 | −1.9% ppl | Recommended |
| Q3_K_M | 3.6 GB | 4.4 GB | 128K | 798 | −5.4% ppl | Long context |
| Q2_K | 3.1 GB | 3.9 GB | 128K | 931 | −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 (512 tokens, 7 of 42 layers global), which is why its cache barely grows with context.
How to run it
$ ollama pull gemma4:e4b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run gemma4:e4b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 4.5 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.