Instructions to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp",
	filename="CHADROCK3.6-27B-Coder-MTP-ROCmFP4-STRIX_LEAN.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
llama-cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
llama-cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
./llama-cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Use Docker

docker model run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

LM Studio
Jan

vLLM

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp"
# 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/chadrock3.6-27b-coder-rocmfp4-mtp",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Ollama
How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Ollama:
```
ollama run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
```

Unsloth Studio

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp 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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp 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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open /spaces/unsloth/studio in your browser
# Search for jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp to start chatting

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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": "jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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/chadrock3.6-27b-coder-rocmfp4-mtp

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Docker Model Runner:
```
docker model run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
```

Lemonade

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Run and chat with the model

lemonade run user.chadrock3.6-27b-coder-rocmfp4-mtp-{{QUANT_TAG}}

List all available models

lemonade list

CHADROCK3.6 27B Coder ROCmFP4 MTP

CHADROCK3.6 27B Coder is a Chadrock ROCmFP4/MTP GGUF release of the Qwopus3.6 27B Coder lineage, tuned for AMD Ryzen AI Max+ 395 / Strix Halo systems.

It uses the Qwopus3.6 27B Coder MTP line as upstream lineage, then converts that source into Charlie's AMD-focused ROCmFP4 Strix Lean runtime format. The public release name and artifact names are Chadrock names, while Qwopus stays explicit in lineage, base model metadata, and credits. The result is a compact 14 GB GGUF for local agentic coding, repository work, tool-use style prompts, and long-context experiments on unified-memory AMD hardware.

This GGUF will not run correctly with stock llama.cpp. It needs the custom charlie12345/rocmfp4-llama build because the file uses ROCmFP4 tensor types that upstream llama.cpp does not currently understand.

The model file is already provided here. You do not need to rebuild or quantize the model. Build the custom llama server once, download the files, and run the profile below.

Why This Build Exists

CHADROCK3.6 27B Coder is the Strix-focused Chadrock release of a dense agentic coding model lineage. It is intended for coding, tool use, debugging, structured developer workflows, and runtime experimentation on AMD hardware. Chadrock adds the AMD runtime piece:

ROCmFP4 Strix Lean tensor recipe
native draft-MTP serving
AMD ROCm/HIP backend path
262K context target
q4_0 KV cache profile for long local sessions
optional vision projector companion file

This release is best treated as a model/runtime pairing for Strix Halo rather than a generic GGUF quant.

Model Lineage

Qwen/Qwen3.6-27B
  -> Jackrong/Qwopus3.6-27B-v2
       datasets:
         - Jackrong/Claude-opus-4.6-TraceInversion-9000x
         - Jackrong/Claude-opus-4.7-TraceInversion-5000x
  -> Jackrong/Qwopus3.6-27B-Coder
       adds:
         - lambda/hermes-agent-reasoning-traces
         - agentic coding and tool-use SFT
  -> Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
  -> jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

In plain terms: Qwen provides the dense 27B foundation, Jackrong's Qwopus line adds Trace Inversion and coder/tool-use training, the upstream MTP GGUF provides the MTP source, and this release converts that line into a Strix-focused ROCmFP4 Chadrock format.

Technical Metadata

Field	Value
model size	`27B` dense
architecture	`qwen35`
local runtime format	ROCmFP4 Chadrock GGUF
direct upstream/source GGUF	`Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF`
upstream behavior lineage	`Jackrong/Qwopus3.6-27B-v2` plus coder SFT
local profile	`qwopus3.6-27b-coder-mtp-chadrock-rocmfp4-strix-lean`
context target	`262144` tokens
draft mode	`draft-mtp`, `n_max=4`, `p_split=0.10`
intended hardware	AMD Ryzen AI Max+ 395 / Strix Halo

Local Benchmark Notes

All numbers below were measured locally on AMD Ryzen AI Max+ 395 / Strix Halo.

BigCodeBench Hard Instruct

Run	Result
`bigcodebench-hard-instruct`, calibrated	`48/148 = 32.43% pass@1`

The scored run used the local profile qwopus3.6-27b-coder-mtp-chadrock-rocmfp4-strix-lean in the June 13 full coding benchmark folder. That local profile name records source lineage and build path; the public release name is CHADROCK3.6 27B Coder.

Apples-to-Apples Q5_K_M Comparison

The cleanest decode-speed comparison is the same CHADROCK CLI guard run against the upstream Qwopus3.6 27B Coder MTP Q5_K_M GGUF and this Chadrock ROCmFP4 build, using the same prompts, runtime build, machine, and MTP guard harness.

Guard row	Upstream Q5_K_M decode	Chadrock ROCmFP4 decode	Decode uplift
short arithmetic prompt	`17.8 tok/s`	`29.5 tok/s`	`1.66x`
sustained regression-guard prompt	`13.2 tok/s`	`22.6 tok/s`	`1.71x`

Prompt processing is better represented by the no-cache long-context sweep below, where Chadrock ROCmFP4 measured 315.97 tok/s at 4K prompt tokens and 142.00 tok/s at 130K prompt tokens.

Long-Context Sweep

The no-cache forced context sweep generated 512 tokens at each context length:

Prompt tokens	Prompt speed	Decode speed	Draft accepted
`4,131`	`315.97 tok/s`	`21.25 tok/s`	`314/779`
`8,227`	`308.66 tok/s`	`21.82 tok/s`	`329/728`
`16,419`	`286.62 tok/s`	`21.64 tok/s`	`344/666`
`32,803`	`251.76 tok/s`	`17.35 tok/s`	`335/701`
`65,571`	`201.49 tok/s`	`12.51 tok/s`	`329/726`
`130,467`	`142.00 tok/s`	`7.08 tok/s`	`305/823`

These are local server measurements, not universal llama.cpp claims. Throughput depends heavily on driver version, clocks, prompt shape, KV cache settings, and MTP acceptance.

Run With llama-server

Build Charlie's custom llama.cpp once, download this GGUF and the projector file, then run:

HSA_OVERRIDE_GFX_VERSION=11.5.1 \
GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
/path/to/rocmfp4-llama/build-strix-rocmfp4/bin/llama-server \
  -m CHADROCK3.6-27B-Coder-MTP-ROCmFP4-STRIX_LEAN.gguf \
  --mmproj mmproj-F32.mmproj \
  --alias chadrock3.6-27b-coder \
  --host 127.0.0.1 \
  --port 8080 \
  --jinja \
  -c 262144 \
  -ngl 999 \
  -fa on \
  -dev ROCm0 \
  -b 512 \
  -ub 512 \
  -t 16 \
  -tb 32 \
  -ctk q4_0 \
  -ctv q4_0 \
  --spec-type draft-mtp \
  --spec-draft-device ROCm0 \
  --spec-draft-ngl all \
  --spec-draft-type-k q4_0 \
  --spec-draft-type-v q4_0 \
  --spec-draft-n-max 4 \
  --spec-draft-n-min 0 \
  --spec-draft-p-min 0.0 \
  --spec-draft-p-split 0.10 \
  --parallel 1 \
  --metrics \
  --no-mmap

Use --parallel 1 for this MTP profile. Multi-slot serving changes draft-MTP behavior and is not the intended configuration.

For text-only use, you may omit --mmproj.

For vision use, keep mmproj-F32.mmproj beside the main GGUF, but run with MTP off. In practice, that means using the vision projector and removing the --spec-* draft-MTP flags from the command.

The projector is a GGUF-format projector file with a .mmproj repo extension so Hugging Face's GGUF metadata badge tracks the 27B language model rather than the smaller projector.

Build The Required llama.cpp

git clone https://github.com/charlie12345/rocmfp4-llama.git
cd rocmfp4-llama
git checkout mtp-rocmfp4-strix
env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh

The server binary will be here:

build-strix-rocmfp4/bin/llama-server

About ROCmFP4 / Chadrock

Charlie's ROCmFP4 method adds AMD-focused GGUF tensor formats and backend paths to llama.cpp.

ROCmFP4 is not stock Q4, MXFP4, or NVFP4. It uses custom 4-bit tensor layouts, Codebook10 values, finite unsigned E4M3 scale semantics, tensor-aware Strix presets, ROCm/HIP kernels, Vulkan support, and MTP regression guards.

Why it matters: Strix Halo has a large unified-memory pool, but good local serving still depends on memory bandwidth, tensor layout, KV traffic, and draft-token acceptance. Chadrock is built for that exact hardware shape.

Files

File	Size	SHA256
`CHADROCK3.6-27B-Coder-MTP-ROCmFP4-STRIX_LEAN.gguf`	`14 GB`	`9536a6d9d56708a6b9e94cde00bde59a1788834ce58fa3b37eabfa8626e325d0`
`mmproj-F32.mmproj`	`889 MB`	`32f7ea0600c07272547da401d460f8abbd980f3a57b69d6df87be0e2505e0b9c`

Credits

Qwen: Qwen/Qwen3.6-27B base model family.
Jackrong: Qwopus3.6 v2, Qwopus3.6 27B Coder, Trace Inversion datasets, coder/tool-use SFT, and the MTP GGUF source.
lambda: lambda/hermes-agent-reasoning-traces, included by the upstream coder release.
charlie12345 / @Italianclownz: ROCmFP4 llama.cpp fork, Strix Halo build path, and AMD-focused MTP runtime work.

Notes

This is an experimental AMD ROCmFP4/MTP build. It is intended for local evaluation, coding workflows, and runtime experimentation on compatible AMD hardware.

Downloads last month: -

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/chadrock3.6-27b-coder-rocmfp4-mtp

Base model

Jackrong/Qwopus3.6-27B-v2

Adapter

Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF

Quantized

(2)

this model

jcbtc
/

chadrock3.6-27b-coder-rocmfp4-mtp