Instructions to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF",
	filename="ThinkingCap-Qwen3.6-27B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Ollama:
```
ollama run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
```

Unsloth Studio

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF to start chatting

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Docker Model Runner:
```
docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M
```

Lemonade

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF-Q4_K_M

List all available models

lemonade list

ThinkingCap-Qwen3.6-27B — MagicQuant hybrid GGUFs (Q4 / Q5 / Q6)

Per-tensor-group hybrid quantizations of bottlecapai/ThinkingCap-Qwen3.6-27B (a Qwen3.6-27B finetune tuned for efficient thinking — comparable capability with ~50% fewer thinking tokens on average) found by MagicQuant evolutionary search: a measured Predict→Measure→Learn loop with real perplexity + KL-divergence guard on every surviving candidate, imatrix-weighted encoding, and stream-aware sampling. Each tier's per-group precision layout was selected from 16 fully-measured candidate hybrids rather than applied uniformly.

Text-only. The base is a Qwen3.5-VL vision-language model; the vision tower was dropped during conversion, so these are text (LLM) quants — no image input.

The embedded MTP (multi-token-prediction) head is preserved, so these work with llama.cpp speculative decoding using the same file as its own draft model.

Files

File	Size	PPL (wikitext-2)	vs BF16 baseline (6.7803)	Layout
`ThinkingCap-Qwen3.6-27B-Q4_K_M.gguf`	14.65 GiB	6.8931	+0.113	attn/FFN/embed Q4_K_M, head Q6_K
`ThinkingCap-Qwen3.6-27B-Q5_K_M.gguf`	20.89 GiB	6.8270	+0.047	uniform Q6_K (search winner for the tier)
`ThinkingCap-Qwen3.6-27B-Q6_K.gguf`	23.00 GiB	6.8304	+0.050	mixed: E/K/O BF16, U Q6_K, D IQ4_NL, attn-Q MXFP4

All measured identically: 100 chunks, ctx 512, wikitext-2, on an AMD Strix Halo APU (gfx1151). The search converged over 3 rounds (mean abs residual 2.20 → 1.56). Q5 and Q6 land within measurement noise of each other (~0.05 above the BF16 baseline); Q5's lean uniform-Q6_K config is 2 GiB smaller for essentially the same quality.

MTP speculative decoding

The embedded nextn/MTP head is preserved in every file. Serve with the model as its own draft:

llama-server -m ThinkingCap-Qwen3.6-27B-Q4_K_M.gguf \
  -md ThinkingCap-Qwen3.6-27B-Q4_K_M.gguf --spec-type draft-mtp \
  -c 8192 -ngl 99 -fa on -ctk q8_0 -ctv q8_0

Requires a llama.cpp build with qwen35/qwen3.6 arch + MTP (--spec-type draft-mtp) support.

Notes

Chat template is embedded (no patching needed); architecture qwen35.
Group legend: E=embeddings, H=lm head, Q/K/O=attention, U/D=FFN up/down, S=SSM (mamba) ops.
This is a hybrid (linear-attention + attention) architecture; SSM conv/1D tensors are kept at F32 where the block size requires it.
Sibling repo with AMD-native (ROCmFPX fork-only) builds of the same layouts: lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF.

Built with Foundry + MagicQuant (evolutionary per-tensor-group hybrid quantization; measured search with imatrix + KL guard).

Downloads last month: -

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

bottlecapai/ThinkingCap-Qwen3.6-27B

Quantized

(14)

this model