Yes — with 2.5 GB to spare
Olmo 3 7B Instruct at Q4_K_M fits your GeForce RTX 2080 Ti entirely on the GPU at 8K context, at an estimated 91 tokens per second. Past 27K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Fully open — training data and code included. Full multi-head attention, so its cache is 4× a GQA 7B at the same context.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 13.6 GB | 16.7 GB | — | ~4.8 | Reference | 7.0 GB over |
| Q8_0 | 7.2 GB | 10.3 GB | 3K | ~29 | −0.1% ppl | 0.6 GB over |
| Q6_K | 5.6 GB | 8.7 GB | 16K | 67 | −0.4% ppl | Fits |
| Q5_K_M | 4.8 GB | 7.9 GB | 22K | 77 | −0.8% ppl | Long context |
| Q4_K_M | 4.1 GB | 7.2 GB | 27K | 91 | −1.9% ppl | Recommended |
| Q3_K_M | 3.3 GB | 6.4 GB | 34K | 112 | −5.4% ppl | Long context |
| Q2_K | 2.8 GB | 5.9 GB | 38K | 131 | −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 (4096 tokens, 8 of 32 layers global), which is why its cache barely grows with context.
How to run it
$ ollama pull olmo-3:7b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run olmo-3:7b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.