Instructions to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-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 dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-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 dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

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 dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

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 dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-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": "dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

Ollama
How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF with Ollama:
```
ollama run hf.co/dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4
```
Unsloth Desktop

How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

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": "dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4
```

Lemonade

How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-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 dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

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 dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4

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 "dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF:NVFP4" \
  --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"

Qwen3.8-27B Heretic ARA ModelOpt NVFP4 GGUF

Text-only GGUF conversion of PassingByPixels/Qwen3.8-27B-heretic-ara-NVFP4, paired with a compact Q4_K_M MTP-only draft model.

Lineage

Qwen/Qwen3.8-27B
  -> trohrbaugh/Qwen3.8-27B-heretic-ara
  -> PassingByPixels/Qwen3.8-27B-heretic-ara-NVFP4
  -> this GGUF conversion

Heretic ARA source: 1-pass ARA checkpoint, reported KL divergence 0.0535.
Quantization: NVIDIA ModelOpt NVFP4 W4A4, group size 16.
Conversion: official llama.cpp b10453, --outtype auto --no-nextn.
GGUF payload: 1,651 tensors; 400 native NVFP4 tensors (GGML_TYPE_NVFP4).
This is not the RVN 3-pass checkpoint and does not claim RVN's reported KL value.
No Q4/K-quant checkpoint was used as a quantization source.

Files

File	Purpose	SHA-256
`Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4.gguf`	Target model	`579661c0a28696feae61110f19f6d8509c142f8ee91f01b0f3924dac511513bd`
`Qwen3.8-27B-MTP-ONLY-Q4_K_M.gguf`	MTP draft model	`a120e79f1f517ecb2737005d446649b1d3431864330db2086a26f22b49a2be8d`

The MTP file is derived from the original Qwen3.8-27B MTP head and is compatible with Qwen3.8-27B derivatives. It is not trained on the Heretic weights.

llama.cpp

Requires a recent CUDA build with Qwen3.8, NVFP4, and draft-MTP support. Native FP4 execution requires NVIDIA Blackwell.

llama-server \
  -m Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4.gguf \
  -c 262144 -np 1 --kv-unified -ngl all -fa on \
  -ctk q8_0 -ctv q4_0 \
  --spec-type draft-mtp \
  --spec-draft-model Qwen3.8-27B-MTP-ONLY-Q4_K_M.gguf \
  --spec-draft-n-max 3 -ctkd q4_0 -ctvd q4_0 \
  -b 512 -ub 256 -fit off \
  --jinja --reasoning on --reasoning-preserve

Disable thinking per request:

{"chat_template_kwargs":{"enable_thinking":false}}

RTX 5090 validation

Tested on one GeForce RTX 5090 32 GB with llama.cpp b10453, CUDA 13.3 runtime, 262,144 allocated context, one slot, Flash Attention, K Q8_0 / V Q4_0 target KV, and Q4_0 draft KV.

Workload	Target tok/s	MTP accepted/generated	Acceptance	Mean draft length
Korean prose, 512 tokens	72.80	269/722	37.26%	2.12
Python code, 512 tokens	124.39	369/423	87.23%	3.62
Repetitive text, 512 tokens	135.76	381/388	98.20%	3.93

Load VRAM: approximately 27.22 GB.
Post-request VRAM: approximately 27.25 GB.
A 9,476-token retrieval prompt completed without OOM: 68.17 prompt tok/s and 21.09 generation tok/s.
Draft maxima 3, 5, and 7 were tested. 3 was retained because 5 and 7 reduced throughput on low-acceptance prose.
enable_thinking=false, Korean and English output, coding, authentication, start/stop, and VRAM release were tested through the OpenAI-compatible API.

These are single-system smoke measurements, not general benchmark claims. Throughput depends heavily on prompt structure, MTP acceptance, context length, runtime revision, and GPU state.

Sampling defaults used in validation

temperature       0.6
top_p             0.95
top_k             20
min_p             0.0
presence_penalty  0.0
repeat_penalty    1.0

Limitations

Reduced safety guardrails are inherited from the upstream Heretic ARA checkpoint.
This release is text-only. Vision and video paths were not included or validated.
The runtime KV cache in the documented llama.cpp configuration is Q8_0/Q4_0, not FP8.
Allocating 262K context does not make full-window prefill fast. Long-context attention cost remains substantial.
Quantization is lossy. No full academic evaluation suite was run for this GGUF conversion.

Credits

Qwen — base model.
trohrbaugh — Heretic ARA checkpoint.
PassingByPixels — NVIDIA ModelOpt NVFP4 checkpoint.
a4lg — MTP-only GGUF conversion.
llama.cpp — GGUF conversion and runtime.

License

Apache License 2.0, inherited from the upstream model lineage.

Downloads last month: 975

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF

Base model

trohrbaugh/Qwen3.8-27B-heretic-ara

Quantized

PassingByPixels/Qwen3.8-27B-heretic-ara-NVFP4

Quantized

(1)

this model

Collection including dawncr0w/Qwen3.8-27B-Heretic-ARA-ModelOpt-NVFP4-GGUF

Qwen3.8 Heretic ARA

Collection

Qwen3.8 Heretic ARA releases and deployment-ready quantizations. • 1 item • Updated 14 days ago