Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8
Note: When using 4 GPUs, you must include --enable-expert-parallel because expert tensor TP must be evenly divisible; for 2 GPUs this is not necessary.
Params
30.5 B
Context
262,144
Downloads 30d
163 K
Likes
8
Download history
daily snapshots · 8 days163 K161 K
Oct 18Oct 20Oct 23Oct 25
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 | 32.0 GB | 40.3 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 32.0 GB | 182.3 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-gptq-int8
{
"hf_id": "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8",
"params_b": 30.53,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 162750,
"vram_estimates": [
{ "quant": "i32", "gb": 40.3 }
],
"updated_at": "2026-10-18T01:00:21Z"
}
Specifications
- Architecture
- Qwen3MoeForCausalLM
- Parameters
- 30.5 B
- Tensor type
- I32
- Context length
- 262,144
- Vocabulary
- 151,936
- Layers / heads
- 48 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-08-01
- Base model
- Qwen3-Coder-30B-A3B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-18
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model