Skip to content
localmodel.run

Text model · Qwen2.5-Coder

Qwen2.5 Coder 1.5B requirements

Qwen2.5-Coder family · 1.54B params · released Sep 2024 · 16.8M Ollama pulls. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseApache-2.0· Commercial OK↓ 545.5K/mo♥ 127on HuggingFace
Q4_K_M
0.92 GB
Q8_0
1.53 GB
Total @ Q4 (4k)
~2 GB
Context
32 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K0.6 GB est
Q3_K_M0.8 GB est
Q4_K_M (default)0.92 GB
Q5_K_M1.1 GB est
Q6_K1.3 GB est
Q8_01.53 GB
FP163.1 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:1.5b
llama.cpp
$ llama-cli -hf bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF

Which devices can run Qwen2.5 Coder 1.5B?

FAQ

How much VRAM or RAM does Qwen2.5 Coder 1.5B need?

At Q4_K_M, Qwen2.5 Coder 1.5B needs about 2 GB (weights ~0.92 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~2.6 GB.

Can Qwen2.5 Coder 1.5B run on a laptop?

Yes, Qwen2.5 Coder 1.5B 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 1.5B commercially?

Yes. Qwen2.5 Coder 1.5B 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 context.

Sources

Memory figures are estimates. See methodology.