Qwen3-Coder-30B-A3B-Instruct-AWQ
AWQ W4A16 (4-bit weights, group size 128) quantization of Qwen/Qwen3-Coder-30B-A3B-Instruct, produced with llm-compressor for serving on a single 24 GB GPU with vLLM.
Params
30.0 B
Context
262,144
Downloads 30d
155 K
Likes
3
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)155 K downloads in the last 30 days
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 | 16.7 GB | 23.4 GB | ⚠️ Tight — reduce context |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 16.7 GB | 162.9 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 -s https://aimodelscomparison.com/api/v1/models/qwen3-coder-30b-a3b-instruct-awq-dark-side-of-the-code
{
"hf_id": "dark-side-of-the-code/Qwen3-Coder-30B-A3B-Instruct-AWQ",
"params_b": 30.00,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 154637,
"vram_estimates": [
{ "quant": "i32", "gb": 23.4 }
],
"updated_at": "2026-11-06T01:00:16Z"
}
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
- 2026-07-13
- Base model
- Qwen3-Coder-30B-A3B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-06
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model