Qwen / text-generation Open weights updated 1 year ago

Qwen2.5-Coder-0.5B-Instruct

Name: Qwen2.5-Coder-0.5B-Instruct
Author: Qwen

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

494 M

Context

32,768

Downloads 30d

145 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 23 days

202 K144 K

Oct 3Oct 10Oct 18Oct 25

Can you run it?

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

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	1.0 GB	1.7 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 32K ctx	1.0 GB	1.9 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-0-5b-instruct
{
  "hf_id": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
  "params_b": 0.49,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 144803,
  "vram_estimates": [
    { "quant": "bf16", "gb": 1.7 }
  ],
  "updated_at": "2026-10-03T01:00:15Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 494 M
Tensor type: BF16
Context length: 32,768
Vocabulary: 151,936
Layers / heads: 24 / 14
Licence: apache-2.0
First seen on the Hub: 2024-11-06
Training datasets: undisclosed
Added to our catalog: 2026-10-03

Compare with any text-generation model

Popular comparisons

Qwen3-0.6B 24.9 M gpt2 20.1 M Qwen2.5-0.5B-Instruct 5.3 M Qwen2.5-1.5B-Instruct 4.7 M Llama-3.2-1B-Instruct 3.7 M pythia-160m 3.4 M

Appears in

Best open coding models