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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-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-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

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-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

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-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

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-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

Use Docker

docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

LM Studio
Jan

vLLM

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

Ollama
How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF with Ollama:
```
ollama run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16
```

Unsloth Studio

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-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-ROCmFPX-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-ROCmFPX-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-ROCmFPX-GGUF to start chatting

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-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-ROCmFPX-GGUF:F16

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-ROCmFPX-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-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-ROCmFPX-GGUF:F16

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-ROCmFPX-GGUF:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-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-ROCmFPX-GGUF:F16

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-ROCmFPX-GGUF:F16" \
  --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-ROCmFPX-GGUF with Docker Model Runner:
```
docker model run hf.co/lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF:F16

Run and chat with the model

lemonade run user.ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF-F16

List all available models

lemonade list

ThinkingCap-Qwen3.6-27B — ROCmFPX × MagicQuant hybrid GGUFs (AMD-native, fork-only)

⚠️ These files do NOT load on standard llama.cpp

They use AMD-native *_ROCMFPX tensor types from the experimental ciru-ai/ROCmFPX llama.cpp fork (build from source). For files that work with stock llama.cpp / LM Studio / Ollama, use the sibling repo: lmcoleman/ThinkingCap-Qwen3.6-27B-MagicQuant-GGUF.

ROCm-optimized versions of MagicQuant-optimized quants: each file reproduces a MagicQuant evolutionary-search winner's per-tensor-group precision layout (selected by measured perplexity + KL divergence against the BF16 base) re-expressed in ROCmFPX's AMD-native tensor types via llama-quantize --tensor-type-file. Tuned for and benchmarked on AMD Strix Halo (Radeon 8060S iGPU, gfx1151, unified memory).

Vision-capable. The base is a Qwen3.5-VL vision-language model. These are the quantized text model in ROCmFPX types; pair any with the included mmproj-ThinkingCap-Qwen3.6-27B-f16.gguf (f16 vision projector, 0.86 GiB) for image input: llama-server -m <file>.gguf --mmproj mmproj-ThinkingCap-Qwen3.6-27B-f16.gguf -ngl 99 -fa on.

Files

File	Size	Layout source (measured PPL of the K-quant twin)
`...ROCMFPX-MQ-Q4.gguf`	14.64 GiB	MagicQuant Q4 tier (PPL 6.8931)
`...ROCMFPX-MQ-Q5.gguf`	20.69 GiB	MagicQuant Q5 tier (PPL 6.8270)
`...ROCMFPX-MQ-Q6.gguf`	23.48 GiB	MagicQuant Q6 tier (PPL 6.8304)

PPL figures are the measured values of the K-quant layout each file reproduces (BF16 baseline 6.7803, wikitext-2, 100 chunks, ctx 512); the ROCmFPX re-expression was not separately PPL-measured. The embedded MTP head is preserved.

Recommended tier: MQ-Q5. Its layout source (uniform Q6_K) measured equal-or-better than the Q6 tier's hybrid (6.8270 vs 6.8304 — a 0.003 gap against ±0.107 measurement noise, i.e. a statistical tie) with better mean KL divergence, at 2.8 GiB smaller. The MQ-Q6 file's extra size buys nothing measurable here; tiers are independent size-band search winners, not supersets, so small inversions like this are expected behavior.

MTP speculative decoding

With the fork's llama-server:

llama-server -m ThinkingCap-Qwen3.6-27B-ROCMFPX-MQ-Q5.gguf \
  -md ThinkingCap-Qwen3.6-27B-ROCMFPX-MQ-Q5.gguf --spec-type draft-mtp \
  -c 8192 -ngl 99 -fa on -ctk q8_0 -ctv q8_0

Notes

Chat template embedded; architecture qwen35. No patching needed.
Experimental upstream research build. Known-good commit these files were built and validated with:

git clone https://github.com/ciru-ai/ROCmFPX && cd ROCmFPX
git checkout 221402af8574faf652b101b6afe225a3f329561f

Source: a Qwen3.6-27B finetune (efficient thinking, ~50% fewer thinking tokens).
Built with Foundry + MagicQuant: evolutionary per-group hybrid search (measured, imatrix-weighted, KL-guarded), layouts exported to ROCmFPX types per group.

Downloads last month: 5,132

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

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

Base model

Qwen/Qwen3.6-27B

Finetuned

bottlecapai/ThinkingCap-Qwen3.6-27B

Quantized

(46)

this model