JunHowie / text-generation updated 11 months ago

Qwen3-14B-GPTQ-Int4

Name: Qwen3-14B-GPTQ-Int4
Author: JunHowie

This model is quantized to 4-bit with a group size of 128. Compared to earlier quantized versions, the new quantized model demonstrates better tokens/s efficiency. This improvement comes from setting descact=False in the quantization configuration.

Params

14.8 B

Context

40,960

Downloads 30d

194 K

Likes

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

Download history

daily snapshots · 10 days

240 K194 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	i32	10.0 GB	13.7 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 40K ctx	10.0 GB	22.6 GB	⚠️ Tight — reduce context

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/qwen3-14b-gptq-int4
{
  "hf_id": "JunHowie/Qwen3-14B-GPTQ-Int4",
  "params_b": 14.77,
  "context_length": 40960,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 193508,
  "vram_estimates": [
    { "quant": "i32", "gb": 13.7 }
  ],
  "updated_at": "2026-07-28T18:07:25Z"
}

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

Specifications

Architecture: Qwen3ForCausalLM
Parameters: 14.8 B
Tensor type: I32
Context length: 40,960
Vocabulary: 151,936
Layers / heads: 40 / 40
Licence: apache-2.0
First seen on the Hub: 2025-04-30
Base model: Qwen3-14B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3-14B Qwen 2.8 M

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