Qwen / text-generation Open weights Also via API updated 1 year ago

Qwen3-235B-A22B-Instruct-2507

Name: Qwen3-235B-A22B-Instruct-2507
Price: 0.14 USD
Author: Qwen

We introduce the updated version of the Qwen3-235B-A22B non-thinking mode, named Qwen3-235B-A22B-Instruct-2507, featuring the following key enhancements:

Params

235.1 B

Context

262,144

Downloads 30d

139 K

Likes

813

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

Download history

daily snapshots · 50 days

▲ 45 K in the last 30 days (24.3%)

211 K139 K

Sep 22Oct 8Oct 25Nov 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	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 · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-235b-a22b-instruct-2507
{
  "hf_id": "Qwen/Qwen3-235B-A22B-Instruct-2507",
  "params_b": 235.09,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 139396,
  "vram_estimates": [
    { "quant": "bf16", "gb": 553.0 }
  ],
  "updated_at": "2026-09-22T01:00:24Z"
}

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

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.14

input / 1M

$0.80

output / 1M

$0.05

cached input / 1M

$0.94

1M in + 1M out

Context window: 131,072 tokens
Max output: 117,964 tokens
Providers: 4
Cheapest provider: GMICloud · $0.088 / $0.35
Best throughput: —
AA Intelligence / Coding / Agentic: — / — / —

✓ 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: 2025-07-21
Training datasets: undisclosed
Added to our catalog: 2026-09-22

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 7.6 M DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF 3.3 M DeepSeek-V4-Flash-0731 2.7 M gpt-oss-120b 2.4 M MiniMax-M2.5 1.2 M Hy3 1.2 M