Yes — with 8.7 GB to spare
Mistral 7B Instruct v0.3 at Q4_K_M fits your RTX 2000 Ada entirely on the GPU at 8K context, at an estimated 33 tokens per second. There is room for its full 32K window.
Fully on GPU
8K context
Q4_K_M · 4.1 GB
Apache 2.0
Released May 2024
Old but extremely well behaved, and permissively licensed for commercial use.
The VRAM budget
weights 4.1 GB
Weights 4.1 GB
KV cache @ 8K 1.00 GB
Runtime overhead 0.6 GB
Free 8.7 GB of 14.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 13.5 GB | 15.1 GB | 2K | ~8.8 | Reference | 0.7 GB over |
| Q8_0 | 7.2 GB | 8.8 GB | 32K | 19 | −0.1% ppl | Long context |
| Q6_K | 5.5 GB | 7.1 GB | 32K | 24 | −0.4% ppl | Long context |
| Q5_K_M | 4.8 GB | 6.4 GB | 32K | 28 | −0.8% ppl | Long context |
| Q4_K_M | 4.1 GB | 5.7 GB | 32K | 33 | −1.9% ppl | Recommended |
| Q3_K_M | 3.3 GB | 4.9 GB | 32K | 41 | −5.4% ppl | Long context |
| Q2_K | 2.8 GB | 4.4 GB | 32K | 48 | −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 mistral:7b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run mistral:7b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 4.1 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.