Instructions to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 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 jcbtc/qwable-5-27b-chadrock-v2-rocmfp4
# Run inference directly in the terminal:
llama cli -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4
# Run inference directly in the terminal:
llama cli -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

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 jcbtc/qwable-5-27b-chadrock-v2-rocmfp4
# Run inference directly in the terminal:
./llama-cli -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

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 jcbtc/qwable-5-27b-chadrock-v2-rocmfp4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Use Docker

docker model run hf.co/jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

LM Studio
Jan

vLLM

How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jcbtc/qwable-5-27b-chadrock-v2-rocmfp4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jcbtc/qwable-5-27b-chadrock-v2-rocmfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Ollama
How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with Ollama:
```
ollama run hf.co/jcbtc/qwable-5-27b-chadrock-v2-rocmfp4
```
Unsloth Desktop

How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jcbtc/qwable-5-27b-chadrock-v2-rocmfp4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with Docker Model Runner:
```
docker model run hf.co/jcbtc/qwable-5-27b-chadrock-v2-rocmfp4
```

Lemonade

How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Run and chat with the model

lemonade run user.qwable-5-27b-chadrock-v2-rocmfp4-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

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 jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jcbtc/qwable-5-27b-chadrock-v2-rocmfp4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

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 "jcbtc/qwable-5-27b-chadrock-v2-rocmfp4" \
  --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"

Qwable 5 27B Chadrock v2 ROCmFP4

Qwable 5 27B Chadrock v2 ROCmFP4 is a Chadrock ROCmFP4/MTP GGUF release of DJLougen/Qwable-5-27B-Coder, tuned for AMD Ryzen AI Max+ 395 / Strix Halo systems.

Qwable is an agentic coding tune of Qwen3.6 27B built for repository work, terminal feedback, tool-use style prompts, and long coding turns. This release keeps that Qwable behavior and converts it into a compact Chadrock ROCmFP4 GGUF for fast served MTP on AMD unified-memory hardware.

This GGUF does not run correctly with stock upstream llama.cpp. It requires the Chadrock ROCmFPX / llama.cpp runner described here:

https://llm.ciru.ai/chadrock-rocmfpx/

The setup page includes the pinned build commands, runner tag, launch config, request-level speculative controls, and validation checks needed to reproduce the speed rows below.

What This Build Is For

Local coding-agent and repository-work prompts on Strix Halo.
Fast one-slot served MTP with request-level speculative.n_max control.
Text-only llama-server use with a compact 14 GB ROCmFP4 GGUF.
Benchmarking Qwable against vanilla Qwen3.6 27B Q4 MTP under the same Chadrock runtime.

Lineage

unsloth/Qwen3.6-27B
  -> DJLougen/Qwable-5-27B-Coder
       training focus:
         - Claude Fable 5 coder-agent traces
         - Kimi 2.7 Coder traces
         - repository work, terminal workflows, tool-use style coding
  -> Qwable 5 27B Chadrock v2 ROCmFP4

The source model card for Qwable is Apache-2.0 and describes the model as a Qwen3.6-based coder-agent tune for real coding loops: inspect, edit, verify, and recover.

File

File	Size	SHA256
`Qwable-5-27B-Chadrock-v2-ROCmFP4.gguf`	`14,817,252,416 bytes`	`87818044a04cdfc0b5b7af897f0cf707273b7e4175b52a55cde8bd5c4bc12e3d`

Best Known Strix Halo Settings

Use the pinned ROCmFPX setup page for the full build and launch guide:

https://llm.ciru.ai/chadrock-rocmfpx/

Current tested text-speed profile:

backend: Vulkan0 target + Vulkan0 draft
context: 131072 tested locally, 262144 model context metadata
batch / ubatch: 2048 / 512
target KV: q8_0 / q8_0
draft KV: f16 / f16
MTP: draft-mtp
startup draft cap: n_max=6, n_min=0, p_min=0.0, p_split=0.20
short-context request policy: speculative.n_max=6
mid-context request policy: speculative.n_max=4
long-context request policy: speculative.n_max=2
serving: one slot, metrics on, text-only for speed runs
sampler: temperature=0, top_p=0.95, top_k=20

Start the server with a draft cap at least as high as the deepest policy you plan to test. A request can lower speculative.n_max, but it cannot raise it above the server startup cap.

Run With Chadrock ROCmFPX

Build the runner from the pinned runner commit:

git clone https://github.com/ciru-ai/ROCmFPX.git
cd ROCmFPX
git checkout 7aa484a2f0a504dc612a3d74a068024f3e6d6353
env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh llama-server llama-bench

Launch the text-speed profile:

MODEL=/path/to/Qwable-5-27B-Chadrock-v2-ROCmFP4.gguf \
ALIAS=qwable-5-27b-chadrock-v2-rocmfp4 \
PORT=18180 \
CTX_SIZE=131072 \
DEVICE=Vulkan0 \
SPEC_DRAFT_DEVICE=Vulkan0 \
BATCH_SIZE=2048 \
UBATCH_SIZE=512 \
CACHE_TYPE_K=q8_0 \
CACHE_TYPE_V=q8_0 \
CACHE_TYPE_K_DRAFT=f16 \
CACHE_TYPE_V_DRAFT=f16 \
SPEC_DRAFT_N_MAX=6 \
SPEC_DRAFT_N_MIN=0 \
SPEC_DRAFT_P_MIN=0.0 \
SPEC_DRAFT_P_SPLIT=0.20 \
CPENT=-1 \
CTXCP=0 \
CACHE_RAM=8192 \
STRICT_BENCH=0 \
scripts/run-rocmfpx-mtp-server.sh

Example /completion request:

curl -sS http://127.0.0.1:18180/completion \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "Write a concise technical note about ROCmFPX MTP serving.",
    "n_predict": 512,
    "temperature": 0,
    "ignore_eos": true,
    "speculative.n_max": 6,
    "speculative.n_min": 0,
    "speculative.p_min": 0.0
  }'

Use --parallel 1 / one slot for MTP speed testing. Multi-slot serving changes draft-MTP behavior and is not the intended profile for these numbers.

Speed Tests vs Vanilla Q4

All numbers below were measured locally on AMD Ryzen AI Max+ 395 / Strix Halo with the same Chadrock Vulkan llama-server runtime, same prompt files, same API harness, same q8_0 target KV, same f16 draft KV, same b2048/u512, temperature=0, 512 generated tokens, and one-slot draft-MTP serving.

The vanilla baseline is the non-Chadrock model file /srv/ssd/sn850x/models/froggeric-Qwen3.6-27B-MTP-GGUF/Qwen3.6-27B-Q4_K_M-mtp.gguf, served on the same Chadrock runtime. These rows compare model/quant behavior under one runtime; they are not stock upstream llama.cpp runtime rows.

Model	Prompt tokens	Request draft setting	Decode tok/s	Prefill tok/s	Full request time	Draft accepted
Qwable 5 27B Chadrock v2 ROCmFP4	3,946	`n6`	`53.25`	`305.33`	`22.55 s`	`438 / 438`
Qwable 5 27B Chadrock v2 ROCmFP4	3,946	`n4`	`45.66`	`306.15`	`24.11 s`	`408 / 408`
Vanilla Qwen3.6 27B Q4_K_M MTP	3,946	`n4`	`27.82`	`264.04`	`33.36 s`	`363 / 588`
Vanilla Qwen3.6 27B Q4_K_M MTP	3,946	`n6`	`25.61`	`263.88`	`34.95 s`	`382 / 771`
Qwable 5 27B Chadrock v2 ROCmFP4	18,766	`n4`	`31.63`	`276.42`	`84.10 s`	`377 / 532`
Vanilla Qwen3.6 27B Q4_K_M MTP	18,766	`n4`	`34.45`	`241.13`	`92.71 s`	`402 / 432`

Readout

At the short 3,946-token prompt point, Qwable 5 Chadrock v2 is much faster even when draft depth is controlled. With both models at n4, Qwable reaches 45.66 tok/s vs vanilla 27.82 tok/s, a 64.1% decode speedup.

The best short-context Qwable row is 53.25 tok/s at n6 because it accepted every generated draft token on that prompt. Giving vanilla the same n6 setting made it slower, not faster: vanilla generated 771 draft tokens but accepted only 382.

At the 18,766-token prompt point, vanilla Q4 decodes faster under n4, but Qwable still prefills faster and finishes the full 512-token request sooner overall: 84.10 s vs 92.71 s.

Benchmark Provenance

Local run directory:

/home/crown/bench-results/llama/qwable-5-27b-chadrock-v2-rocmfp4-vs-vanilla-q4-20260621/

Imported benchmark labels:

qwable-5-27b-chadrock-v2-rocmfp4-dynamic-n6-ctx4k-g512
qwable-5-27b-chadrock-v2-rocmfp4-n4-ctx4k-g512
qwable-5-27b-chadrock-v2-rocmfp4-dynamic-n4-ctx16k-g512
vanilla-qwen3-6-27b-q4-k-m-mtp-n4-ctx4k-g512
vanilla-qwen3-6-27b-q4-k-m-mtp-n6-ctx4k-g512
vanilla-qwen3-6-27b-q4-k-m-mtp-n4-ctx16k-g512

The local benchmark store verified cleanly after import.

Credits

DJLougen: Qwable 5 27B Coder source model and coder-agent training.
Unsloth and Qwen: Qwen3.6 27B base model path used by the source checkpoint.
froggeric: Qwen3.6 27B MTP GGUF vanilla Q4 baseline used for local comparison rows.
Ciru / Chadrock ROCmFPX: ROCmFP4 GGUF conversion, Strix Halo serving profile, and pinned runner setup.

Notes

This is an experimental AMD ROCmFP4/MTP release for local evaluation and runtime experimentation. Speeds are hardware-sensitive and depend on driver version, clocks, prompt shape, KV cache settings, and draft-token acceptance.

Downloads last month: 610

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for jcbtc/qwable-5-27b-chadrock-v2-rocmfp4

Base model

Qwen/Qwen3.6-27B

Finetuned

DJLougen/Qwable-5-27B-Coder

Quantized

(6)

this model