Qwen / text-generation updated 1 year ago

Qwen2.5-Math-1.5B

Name: Qwen2.5-Math-1.5B
Author: Qwen

> [!Warning] > > > 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. > >

Params

1.5 B

Context

4,096

Downloads 30d

208 K

Likes

114

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

Download history

daily snapshots · 48 days

▲ 605 K in the last 30 days (74.4%)

860 K208 K

Aug 5Aug 21Sep 6Sep 21

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	3.1 GB	4.1 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-math-1-5b
{
  "hf_id": "Qwen/Qwen2.5-Math-1.5B",
  "params_b": 1.54,
  "context_length": 4096,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 207749,
  "vram_estimates": [
    { "quant": "bf16", "gb": 4.1 }
  ],
  "updated_at": "2026-08-05T01:00:28Z"
}

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

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 1.5 B
Tensor type: BF16
Context length: 4,096
Vocabulary: 151,936
Layers / heads: 28 / 12
Licence: apache-2.0
First seen on the Hub: 2024-09-16
Base model: Qwen2.5-1.5B
Training datasets: undisclosed
Added to our catalog: 2026-08-05

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen2.5-1.5B Qwen 860 K

Compare with any text-generation model

Popular comparisons

Qwen3-0.6B 23.7 M Qwen2.5-1.5B-Instruct 7.4 M Llama-3.2-1B-Instruct 6.9 M Ternary-Bonsai-27B-mlx-2bit 1.1 M Qwen2-1.5B-Instruct 601 K SmolLM-1.7B-Instruct-quantized.w4a16 571 K