cyankiwi / text-generation Open weights updated 3 weeks ago

Qwen3-30B-A3B-Instruct-2507-AWQ-4bit

Name: Qwen3-30B-A3B-Instruct-2507-AWQ-4bit
Author: cyankiwi

Version llm-compressor Calibration nvidia/Llama-Nemotron-Post-Training-Dataset Model Size 18.09 GB

Params

30.0 B

Context

262,144

Downloads 30d

142 K

Likes

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

Download history

daily snapshots · 106 days

▲ 62 K in the last 30 days (30.3%)

898 K142 K

Jul 28Sep 1Oct 6Nov 10

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	18.1 GB	24.9 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	18.1 GB	164.4 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/qwen3-30b-a3b-instruct-2507-awq-4bit
{
  "hf_id": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit",
  "params_b": 30.00,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 142312,
  "vram_estimates": [
    { "quant": "i32", "gb": 24.9 }
  ],
  "updated_at": "2026-10-20T01:00:15Z"
}

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

Specifications

Architecture: Qwen3MoeForCausalLM
Parameters: 30.0 B
Tensor type: I32
Context length: 262,144
Vocabulary: 151,936
Layers / heads: 48 / 32
Licence: apache-2.0
First seen on the Hub: 2025-07-29
Base model: Qwen3-30B-A3B-Instruct-2507
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base Qwen3-30B-A3B-Instruct-2507 Qwen 896 K

Compare with any text-generation model

Popular comparisons

Qwen3-14B 12.9 M Qwen3-4B 4.0 M DeepSeek-R1-0528-Qwen3-8B 371 K granite-4.1-8b 192 K PowerMoE-3b 171 K Meta-Llama-3-8B 139 K