Qwen3-235B-A22B-Thinking-2507
Over the past three months, we have continued to scale the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-235B-A22B-Thinking-2507, featuring the following key enhancements: - Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human...
Params
235.1 B
Context
262,144
Downloads 30d
16 K
Likes
418
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)16 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 | 470.2 GB | 553.0 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 470.2 GB | 1,646.2 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/qwen3-235b-a22b-thinking-2507
{
"hf_id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
"params_b": 235.09,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 15922,
"vram_estimates": [
{ "quant": "bf16", "gb": 553.0 }
],
"updated_at": "2026-10-19T06:00:49Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.45
input / 1M
$3.50
output / 1M
—
cached input / 1M
$3.95
1M in + 1M out
- Context window
- 128,000 tokens
- Max output
- 16,384 tokens
- Providers
- 1
- Cheapest provider
- Venice · $0.45 / $3.50
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 12.7 / 22.1 / 1.3
✓ Tool calling
✓ Reasoning
✗ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- Qwen3MoeForCausalLM
- Parameters
- 235.1 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 151,936
- Layers / heads
- 94 / 64
- Licence
- apache-2.0
- First seen on the Hub
- 2025-07-25
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model