Yes — with 12.0 GB to spare
Qwen2.5-Coder 14B at Q4_K_M fits your Tesla P40 entirely on the GPU at 8K context, at an estimated 25 tokens per second. Past 71K 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 · 8.3 GB
Apache 2.0
Released Nov 2024
Noticeably better at whole-file edits than the 7B, still comfortable on 12 GB.
The VRAM budget
weights 8.3 GB
Weights 8.3 GB
KV cache @ 8K 1.50 GB
Runtime overhead 0.6 GB
Free 12.0 GB of 22.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 27.6 GB | 29.7 GB | — | ~3.4 | Reference | 7.3 GB over |
| Q8_0 | 14.6 GB | 16.7 GB | 38K | 14 | −0.1% ppl | Long context |
| Q6_K | 11.3 GB | 13.4 GB | 55K | 19 | −0.4% ppl | Long context |
| Q5_K_M | 9.8 GB | 11.9 GB | 64K | 21 | −0.8% ppl | Long context |
| Q4_K_M | 8.3 GB | 10.4 GB | 71K | 25 | −1.9% ppl | Recommended |
| Q3_K_M | 6.7 GB | 8.8 GB | 80K | 31 | −5.4% ppl | Long context |
| Q2_K | 5.8 GB | 7.9 GB | 85K | 36 | −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 qwen2.5-coder:14b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen2.5-coder:14b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 8.3 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 71K context on this card.