Yes — with 13.7 GB to spare
Mistral NeMo 12B at Q4_K_M fits your RTX A5000 entirely on the GPU at 8K context, at an estimated 68 tokens per second. Past 95K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Fully on GPU
8K context
Q4_K_M · 6.9 GB
Apache 2.0
Released Jul 2024
Multilingual 12B with a 128K window, built with NVIDIA. A roleplay and fiction favourite that refuses to die.
The VRAM budget
weights 6.9 GB
Weights 6.9 GB
KV cache @ 8K 1.25 GB
Runtime overhead 0.6 GB
Free 13.7 GB of 22.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 22.7 GB | 24.6 GB | — | ~9.6 | Reference | 2.2 GB over |
| Q8_0 | 12.1 GB | 13.9 GB | 62K | 39 | −0.1% ppl | Long context |
| Q6_K | 9.3 GB | 11.2 GB | 79K | 50 | −0.4% ppl | Long context |
| Q5_K_M | 8.1 GB | 9.9 GB | 87K | 58 | −0.8% ppl | Long context |
| Q4_K_M | 6.9 GB | 8.7 GB | 95K | 68 | −1.9% ppl | Recommended |
| Q3_K_M | 5.6 GB | 7.4 GB | 103K | 84 | −5.4% ppl | Long context |
| Q2_K | 4.8 GB | 6.6 GB | 109K | 98 | −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-nemo:12b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run mistral-nemo:12b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 6.9 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 95K context on this card.