empero-ai / text-generation Open weights updated 2 months ago

Qwen3.8-4B-Distill

Name: Qwen3.8-4B-Distill
Author: empero-ai

> [!Note] > This repository contains model weights and configuration files in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, and other standard runtimes with Qwen3.5 architecture support.

Params

4.7 B

Context

—

Downloads 30d

258 K

Likes

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

Download history

daily snapshots · 7 days

258 K165 K

Oct 18Oct 20Oct 22Oct 24

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	9.3 GB	11.5 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/qwen3-8-4b-distill
{
  "hf_id": "empero-ai/Qwen3.8-4B-Distill",
  "params_b": 4.66,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 258449,
  "vram_estimates": [
    { "quant": "bf16", "gb": 11.5 }
  ],
  "updated_at": "2026-10-18T01:00:13Z"
}

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

Specifications

Architecture: Qwen3_5ForConditionalGeneration
Parameters: 4.7 B
Tensor type: BF16
Licence: apache-2.0
First seen on the Hub: 2026-08-15
Base model: Qwen3.5-4B
Training datasets: undisclosed
Added to our catalog: 2026-10-18

Family

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

Base Qwen3.5-4B Qwen 7.5 M

Compare with any text-generation model

Popular comparisons

Qwen3-4B 11.4 M Qwen3-14B 9.4 M Qwen3-8B 8.1 M Qwen2.5-7B-Instruct 6.4 M Llama-3.1-8B-Instruct 4.9 M Qwen2.5-3B-Instruct 3.8 M