Yes — with 37.2 GB to spare
Gemma 3 1B at Q4_K_M fits your A100 40 GB entirely on the GPU at 8K context, at an estimated 1674 tokens per second. There is room for its full 32K window.
Fully on GPU
8K context
Q4_K_M · 0.6 GB
Gemma Terms of Use
Released Mar 2025
Text-only. Single KV head makes its cache almost free at long context.
The VRAM budget
weights 0.6 GB
Weights 0.6 GB
KV cache @ 8K 0.04 GB
Runtime overhead 0.6 GB
Free 37.2 GB of 38.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 1.9 GB | 2.5 GB | 32K | 505 | Reference | Long context |
| Q8_0 | 1.0 GB | 1.6 GB | 32K | 951 | −0.1% ppl | Long context |
| Q6_K | 0.8 GB | 1.4 GB | 32K | 1233 | −0.4% ppl | Long context |
| Q5_K_M | 0.7 GB | 1.3 GB | 32K | 1426 | −0.8% ppl | Long context |
| Q4_K_M | 0.6 GB | 1.2 GB | 32K | 1674 | −1.9% ppl | Recommended |
| Q3_K_M | 0.5 GB | 1.1 GB | 32K | 2068 | −5.4% ppl | Long context |
| Q2_K | 0.4 GB | 1.0 GB | 32K | 2414 | −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, 1 global in 6), which is why its cache barely grows with context.
How to run it
$ ollama pull gemma3:1b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run gemma3:1b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 0.6 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 32K context on this card.