Qwen3.8 Flash

Facts

Released

2026-08-24 the day the repository was first published on Hugging Face Hugging Face, read 2026-09-24

Licence

other the licence the model card declares Hugging Face, read 2026-09-24

Open weights

Yes the weights are published in this Hugging Face repository Hugging Face, read 2026-09-24

Parameters

180.0 billion counted from the safetensors weight files Hugging Face, read 2026-09-24

Active parameters

61.6 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read 2026-09-24

Knowledge cutoff

Unknown

Context window

• 262,144 tokens the maximum position embeddings in the model configuration model configuration, read 2026-09-24
• 1,000,000 tokens the context length OpenRouter lists OpenRouter, read 2026-09-24

Longest output

• 131,072 tokens the largest output OpenRouter's first provider allows OpenRouter, read 2026-09-24

Tool calling

• Yes the chat template in the tokenizer configuration accepts tool definitions Hugging Face, read 2026-09-24
• Yes OpenRouter lists tools among the supported parameters OpenRouter, read 2026-09-24

Structured output

• Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read 2026-09-24

Reasoning controls

• Yes OpenRouter lists reasoning controls OpenRouter, read 2026-09-24

Inputs and outputs

text, image in, text out Hugging Face, read 2026-09-24

Good for

• Vision: Hugging Face files it under image-text-to-text Hugging Face, read 2026-09-24
• Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read 2026-09-24

Prices

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

Start it with a local runtime

• Ollama

  ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q2_K_XL

• LM Studio

  lms get unsloth/Qwen3.8-Flash-Next-GGUF
  lms server start

• llama.cpp server

  llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q2_K_XL --jinja

• vLLM

  vllm serve Qwen/Qwen3.8-Flash-Next

• SGLang

  sglang serve --model-path Qwen/Qwen3.8-Flash-Next --port 30000

Use it from your harness

Set up for TensorX with the model qwen/qwen3.8-flash-next. Each endpoint page has the same setup for its own address.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "tensorx": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "TensorX",
      "options": {
        "baseURL": "https://api.tensorx.ai/v1",
        "apiKey": "{env:TENSORX_API_KEY}"
      },
      "models": {
        "qwen/qwen3.8-flash-next": {
          "name": "Qwen3.8 Flash",
          "limit": {
            "context": 1000000,
            "output": 131072
          }
        }
      }
    }
  }
}

{
  "providers": {
    "tensorx": {
      "baseUrl": "https://api.tensorx.ai/v1",
      "api": "openai-completions",
      "apiKey": "$TENSORX_API_KEY",
      "models": [
        {
          "id": "qwen/qwen3.8-flash-next"
        }
      ]
    }
  }
}

Other ways to reach it

• OpenRouter, model qwen/qwen3.8-flash

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

• Results the maker published on the model card published by Qwen Hugging Face, read 2026-09-24