LLMSafety / text-generation Open weights updated 5 months ago

Qwen2.5-Math-7B-4bit

Name: Qwen2.5-Math-7B-4bit
Author: LLMSafety

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Params

7.8 B

Context

4,096

Downloads 30d

168 K

Likes

Licence: unknown Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 11 days

194 K168 K

Oct 15Oct 18Oct 22Oct 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	u8	5.5 GB	7.8 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-7b-4bit
{
  "hf_id": "LLMSafety/Qwen2.5-Math-7B-4bit",
  "params_b": 7.82,
  "context_length": 4096,
  "license": { "id": "", "commercial": "unknown" },
  "downloads_30d": 168211,
  "vram_estimates": [
    { "quant": "u8", "gb": 7.8 }
  ],
  "updated_at": "2026-10-15T01:00:22Z"
}

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

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 7.8 B
Tensor type: U8
Context length: 4,096
Vocabulary: 152,064
Layers / heads: 28 / 28
First seen on the Hub: 2026-05-09
Training datasets: undisclosed
Added to our catalog: 2026-10-15

Compare with any text-generation model

Popular comparisons

Qwen3-4B 11.4 M Qwen3-14B 10.0 M Qwen3-8B 8.2 M Qwen2.5-7B-Instruct 6.1 M gpt-oss-20b 5.8 M Llama-3.1-8B-Instruct 4.9 M