unsloth / text-generation updated 1 year ago

Qwen2.5-14B-bnb-4bit

Name: Qwen2.5-14B-bnb-4bit
Author: unsloth

--- basemodel: Qwen/Qwen2.5-14B language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara libraryname: transformers license: apache-2.0 tags: - unsloth - transformers ---

Params

15.2 B

Context

131,072

Downloads 30d

218 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 13 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

232 K218 K

Jul 28Jul 31Aug 3Aug 6

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	9.9 GB	13.7 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	9.9 GB	47.9 GB	❌ Won’t fit

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/qwen2-5-14b-bnb-4bit
{
  "hf_id": "unsloth/Qwen2.5-14B-bnb-4bit",
  "params_b": 15.18,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 218144,
  "vram_estimates": [
    { "quant": "u8", "gb": 13.7 }
  ],
  "updated_at": "2026-07-28T18:07:37Z"
}

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

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 15.2 B
Tensor type: U8
Context length: 131,072
Vocabulary: 152,064
Layers / heads: 48 / 40
Licence: apache-2.0
First seen on the Hub: 2024-09-23
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M Llama-3.1-8B-Instruct 8.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB