Yes — with 12.0 GB to spare

Qwen2.5-Coder 14B at Q4_K_M fits your Tesla M40 24 GB entirely on the GPU at 8K context, at an estimated 21 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.

Hardware requirements What hardware do I need to run Qwen2.5-Coder 14B? →

At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

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

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 27.6 GB 29.7 GB — ~3.2 Reference 7.3 GB over
Q8_0 14.6 GB 16.7 GB 38K 12 −0.1% ppl Long context
Q6_K 11.3 GB 13.4 GB 55K 15 −0.4% ppl Long context
Q5_K_M 9.8 GB 11.9 GB 64K 18 −0.8% ppl Long context
Q4_K_M 8.3 GB 10.4 GB 71K 21 −1.9% ppl Recommended
Q3_K_M 6.7 GB 8.8 GB 80K 26 −5.4% ppl Long context
Q2_K 5.8 GB 7.9 GB 85K 30 −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

terminal
$ 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.
See all models for this rig Compare with another model

Related models on a Tesla M40 24 GB

ModelTotalTok/s est.
Qwen2.5-Coder 7B
7.62B · same family
Q4_K_M · 5.3 GB 41 Runs great
Qwen2.5-Coder 32B
32.8B · same family
Q4_K_M · 21.0 GB 9.5 Tight fit
Qwen3 14B
14.8B · similar size
Q4_K_M · 10.2 GB 21 Runs great
DeepSeek-R1-Distill-Qwen 14B
14.8B · similar size
Q4_K_M · 10.4 GB 21 Runs great
Phi-4 14B
14.7B · similar size
Q4_K_M · 10.4 GB 21 Runs great
Ministral 3 14B
13.9B · similar size
Q4_K_M · 9.7 GB 22 Runs great
Gemma 3 12B
12.2B · similar size
Q4_K_M · 8.3 GB 25 Runs great

Every model against the Tesla M40 24 GB →

Qwen2.5-Coder 14B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
10.4 GB ~7.9 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
10.4 GB 26 Tight fit
GeForce RTX 5080
14.4 GB usable · 960 GB/s
10.4 GB 70 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
10.4 GB 8.1 Tight fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
10.4 GB 73 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
10.4 GB 70 Runs great
M4 Pro · 24 GB
18.0 GB usable · 273 GB/s
10.4 GB 18 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
10.4 GB 27 Runs great

All 114 devices, by tier →