Skip to content
localmodel.run

Text model · Qwen2.5

Qwen2.5 1.5B requirements

Qwen2.5 family · 1.54B params · released 2024-09-19 · 23.2M Ollama pulls. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseApache-2.0· Commercial OK↓ 7.5M/mo♥ 739on HuggingFace
Q4_K_M
1.12 GB
Q8_0
1.89 GB
Total @ Q4 (4k)
~2.2 GB
Context
128 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K0.6 GB est
Q3_K_M0.8 GB est
Q4_K_M (default)1.12 GB
Q5_K_M1.1 GB est
Q6_K1.3 GB est
Q8_01.89 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 qwen2.5:1.5b
llama.cpp
$ llama-cli -hf Qwen/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M
LM Studio
$ lms get Qwen/Qwen2.5-1.5B-Instruct-GGUF

Which devices can run Qwen2.5 1.5B?

FAQ

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

At Q4_K_M, Qwen2.5 1.5B needs about 2.2 GB (weights ~1.12 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~3 GB.

Can Qwen2.5 1.5B run on a laptop?

Yes, Qwen2.5 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 1.5B commercially?

Yes. Qwen2.5 1.5B is licensed Apache-2.0, which permits commercial use.

Strong 1.5B edge model from Alibaba. 128K context, 8K generation. Popular for phone and laptop inference with good multilingual and instruction-following capability.

Sources

Memory figures are estimates. See methodology.