Qwen / text-generation updated 1 year ago

Qwen2.5-Coder-3B-Instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

Params
3.1 B
Context
32,768
Downloads 30d
599 K
Likes
127
Licence: other Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 29 days
599 K179 K
Aug 23Sep 1Sep 11Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 6.2 GB 7.8 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 32K ctx 6.2 GB 9.1 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · curl · api/v1
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-coder-3b-instruct
{
  "hf_id": "Qwen/Qwen2.5-Coder-3B-Instruct",
  "params_b": 3.09,
  "context_length": 32768,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 599149,
  "vram_estimates": [
    { "quant": "bf16", "gb": 7.8 }
  ],
  "updated_at": "2026-08-23T01:00:28Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen2ForCausalLM
Parameters
3.1 B
Tensor type
BF16
Context length
32,768
Vocabulary
151,936
Layers / heads
36 / 16
Licence
other
First seen on the Hub
2024-11-06
Training datasets
undisclosed
Added to our catalog
2026-08-23
Compare with any text-generation model