Yes — with 12.3 GB to spare
Llama 3.1 8B Instruct at Q4_K_M fits your RTX 4000 Ada entirely on the GPU at 8K context, at an estimated 48 tokens per second. Past 106K 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 · 4.5 GB
Llama 3.1 Community
Released Jul 2024
Still the most widely deployed local model, with the largest fine-tune ecosystem. Not the strongest 8B any more.
The VRAM budget
weights 4.5 GB
Weights 4.5 GB
KV cache @ 8K 1.00 GB
Runtime overhead 0.6 GB
Free 12.3 GB of 18.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 15.0 GB | 16.6 GB | 22K | 15 | Reference | Long context |
| Q8_0 | 7.9 GB | 9.5 GB | 78K | 27 | −0.1% ppl | Long context |
| Q6_K | 6.1 GB | 7.7 GB | 93K | 36 | −0.4% ppl | Long context |
| Q5_K_M | 5.3 GB | 6.9 GB | 99K | 41 | −0.8% ppl | Long context |
| Q4_K_M | 4.5 GB | 6.1 GB | 106K | 48 | −1.9% ppl | Recommended |
| Q3_K_M | 3.7 GB | 5.3 GB | 113K | 60 | −5.4% ppl | Long context |
| Q2_K | 3.1 GB | 4.7 GB | 117K | 70 | −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 llama3.1:8b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run llama3.1:8b
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 106K context on this card.