Baltor Get started

Models

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

By Jackrong. 27.8 billion parameters, a context window of 262,144 tokens and the licence apache-2.0.

Facts

Released
2026-02-27 the day the repository was first published on Hugging Face Hugging Face, read
Licence
apache-2.0 the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
27.8 billion counted from the safetensors weight files Hugging Face, read
Active parameters
Unknown
Knowledge cutoff
Unknown
Context window
  • 262,144 tokens the maximum position embeddings in the model configuration model configuration, read
Longest output
Unknown
Tool calling
  • Yes the chat template in the tokenizer configuration accepts tool definitions Hugging Face, read
Structured output
Unknown
Reasoning controls
Unknown
Inputs and outputs
text, image in, text out Hugging Face, read
Good for
  • Vision: Hugging Face files it under image-text-to-text Hugging Face, read

Prices

No source lists a price for this model. It may only run on your own hardware.

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.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
IQ1_S5.8 GiB7.1 GiB8.6 GiB
IQ1_M6.3 GiB7.6 GiB9.1 GiB
IQ2_XXS7.1 GiB8.5 GiB10.0 GiB
IQ2_XS7.8 GiB9.2 GiB10.7 GiB
IQ2_S8.1 GiB9.5 GiB11.0 GiB
IQ2_M8.7 GiB10.2 GiB11.7 GiB
Q2_K_S9.0 GiB10.4 GiB11.9 GiB
Q2_K9.4 GiB10.9 GiB12.4 GiB
IQ3_XXS10.0 GiB11.5 GiB13.0 GiB
IQ3_XS10.8 GiB12.4 GiB13.9 GiB
Q3_K_S11.2 GiB12.8 GiB14.3 GiB
IQ3_S11.3 GiB12.8 GiB14.3 GiB
IQ3_M11.7 GiB13.3 GiB14.8 GiB
Q3_K_M12.4 GiB14.0 GiB15.5 GiB
Q3_K_L13.1 GiB14.7 GiB16.2 GiB
IQ4_XS13.7 GiB15.4 GiB16.9 GiB
Q4_014.5 GiB16.2 GiB17.7 GiB
Q4_K_S14.5 GiB16.2 GiB17.7 GiB
Q4_K_M15.4 GiB17.2 GiB18.7 GiB
Q4_115.9 GiB17.7 GiB19.2 GiB
Q5_K_S17.4 GiB19.3 GiB20.8 GiB
Q5_K_M18.1 GiB20.0 GiB21.5 GiB
Q6_K20.6 GiB22.6 GiB24.1 GiB

Start it with a local runtime

  • Ollama
    ollama run hf.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0
  • LM Studio
    lms get mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF
lms server start
  • llama.cpp server
    llama-server -hf mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0 --jinja
  • vLLM
    vllm serve Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
  • SGLang
    sglang serve --model-path Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled --port 30000

Use it from your harness

Set up for Ollama with the model hf.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "hf.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0": {
          "name": "Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "ollama": {
      "baseUrl": "http://localhost:11434/v1",
      "api": "openai-completions",
      "apiKey": "ollama",
      "models": [
        {
          "id": "hf.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Put this in a terminal:

codex --oss --local-provider ollama -m hf.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0
  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Put this in ~/.claude/settings.json, or variables in your shell:

export ANTHROPIC_BASE_URL="http://localhost:11434"
export ANTHROPIC_AUTH_TOKEN="ollama"
export ANTHROPIC_MODEL="hf.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF:Q4_0"
claude
  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Published results

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