PrimeIntellect / text-generation Open weights updated 1 year ago

Qwen3-0.6B

Name: Qwen3-0.6B
Author: PrimeIntellect

This is a clone of Qwen/Qwen3-0.6B with a multi-turn, tool-call compatible chat template.

Params

752 M

Context

40,960

Downloads 30d

836 K

Likes

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

Download history

daily snapshots · 27 days

836 K200 K

Sep 28Oct 7Oct 16Oct 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	1.5 GB	2.3 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 40K ctx	1.5 GB	2.7 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/qwen3-0-6b-primeintellect
{
  "hf_id": "PrimeIntellect/Qwen3-0.6B",
  "params_b": 0.75,
  "context_length": 40960,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 836153,
  "vram_estimates": [
    { "quant": "bf16", "gb": 2.3 }
  ],
  "updated_at": "2026-09-28T01:00:22Z"
}

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

Specifications

Architecture: Qwen3ForCausalLM
Parameters: 752 M
Tensor type: BF16
Context length: 40,960
Vocabulary: 151,936
Layers / heads: 28 / 16
Licence: apache-2.0
First seen on the Hub: 2025-08-12
Base model: Qwen3-0.6B-Base
Training datasets: undisclosed
Added to our catalog: 2026-09-28

Family

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

Base Qwen3-0.6B-Base Qwen 634 K

Compare with any text-generation model

Popular comparisons

Qwen3-0.6B 25.2 M Qwen2.5-0.5B-Instruct 5.3 M Qwen2.5-1.5B-Instruct 4.8 M Qwen3-1.7B 4.1 M Llama-3.2-1B-Instruct 4.0 M Kimi-K3-DSpark 3.7 M