Qwen3.5-397B-A17B
> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
Params
403.4 B
Context
—
Downloads 30d
667 K
Likes
1,580
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)667 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 | bf16 | 806.8 GB | 948.5 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.50
input / 1M
$3.60
output / 1M
$0.30
cached input / 1M
$4.10
1M in + 1M out
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- Providers
- 10
- Cheapest provider
- Alibaba · $0.39 / $2.34
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 21.4 / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Parameters
- 403.4 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-02-16
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any image-text-to-text model