Skip to content
localmodel.run

Text model · Qwen2.5-Coder

Qwen2.5 Coder 7B requirements

Qwen2.5-Coder family · 7B params · released Sep 2024 · 16.8M Ollama pulls. Minimum to run at Q4_K_M: Nvidia GeForce RTX 3060 (12GB).

LicenseApache-2.0· Commercial OK↓ 1.6M/mo♥ 731on HuggingFace
Q4_K_M
4.36 GB
Q8_0
7.54 GB
Total @ Q4 (4k)
~5.8 GB
Context
32 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K2.9 GB est
Q3_K_M3.4 GB est
Q4_K_M (default)4.36 GB
Q5_K_M5 GB est
Q6_K5.7 GB est
Q8_07.54 GB
FP1614 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run qwen2.5-coder:7b
llama.cpp
$ llama-cli -hf bartowski/Qwen2.5-Coder-7B-Instruct-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/Qwen2.5-Coder-7B-Instruct-GGUF

Which devices can run Qwen2.5 Coder 7B?

FAQ

How much VRAM or RAM does Qwen2.5 Coder 7B need?

At Q4_K_M, Qwen2.5 Coder 7B needs about 5.8 GB (weights ~4.36 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~8.9 GB.

Can Qwen2.5 Coder 7B run on a laptop?

Yes, Qwen2.5 Coder 7B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use Qwen2.5 Coder 7B commercially?

Yes. Qwen2.5 Coder 7B is licensed Apache-2.0, which permits commercial use.

Qwen2.5-Coder, code-specialized. Q4_K_M and Q8_0 sizes from the bartowski GGUF repo. 32K native context, 128K with YaRN.

Sources

Memory figures are estimates. See methodology.