Yes — with 199.5 GB to spare

Qwen2.5-Coder 7B at Q4_K_M fits your CPU only · DDR5 8-channel server entirely on the GPU at 8K context, at an estimated 30 tokens per second. There is room for its full 128K window.

Fully on GPU 8K context Q4_K_M · 4.3 GB Apache 2.0 Released Nov 2024

The standard local autocomplete model — small enough to keep resident all day, and still the best FIM model under 8B.

Hardware requirements What hardware do I need to run Qwen2.5-Coder 7B? →

At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 4.3 GB
Weights 4.3 GB KV cache @ 8K 0.44 GB Runtime overhead 0.6 GB Free 199.5 GB of 204.8 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 14.2 GB 15.2 GB 128K 9.1 Reference Long context
Q8_0 7.5 GB 8.6 GB 128K 17 −0.1% ppl Long context
Q6_K 5.8 GB 6.9 GB 128K 22 −0.4% ppl Long context
Q5_K_M 5.0 GB 6.1 GB 128K 26 −0.8% ppl Long context
Q4_K_M 4.3 GB 5.3 GB 128K 30 −1.9% ppl Recommended
Q3_K_M 3.5 GB 4.5 GB 128K 37 −5.4% ppl Long context
Q2_K 3.0 GB 4.0 GB 128K 43 −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
$ llama-server \
    -hf Qwen/Qwen2.5-Coder-7B-Instruct:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 4.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02With no GPU, thread count matters more than clock. Start at one thread per physical core.
03There is room to go to the model's full 128K context on this card.
See all models for this rig Compare with another model

Related models on a CPU only · DDR5 8-channel server

ModelTotalTok/s est.
Qwen2.5-Coder 14B
14.8B · same family
Q4_K_M · 10.4 GB 15 Runs great
Qwen2.5-Coder 32B
32.8B · same family
Q4_K_M · 21.0 GB 7.0 Runs great
DeepSeek-R1-Distill-Qwen 7B
7.62B · similar size
Q4_K_M · 5.3 GB 30 Runs great
Ling 3.0 Tiny 7.9B-A1.3B
7.9B MoE · similar size
Q4_K_M · 5.1 GB 78 Runs great
Olmo 3 7B Instruct
7.3B · similar size
Q4_K_M · 7.2 GB 31 Runs great
Gemma 4 E4B
8.0B · similar size
Q4_K_M · 5.2 GB 29 Runs great
Mistral 7B Instruct v0.3
7.25B · similar size
Q4_K_M · 5.7 GB 32 Runs great

Every model against the CPU only · DDR5 8-channel server →

Qwen2.5-Coder 7B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
5.3 GB 36 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
5.3 GB 51 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
5.3 GB 16 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
5.3 GB 142 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
5.3 GB 136 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
5.3 GB 52 Runs great

All 114 devices, by tier →