Instructions to use lackonendes/PAW-27B-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 lackonendes/PAW-27B-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 lackonendes/PAW-27B-GGUF
# Run inference directly in the terminal:
llama cli -hf lackonendes/PAW-27B-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lackonendes/PAW-27B-GGUF
# Run inference directly in the terminal:
llama cli -hf lackonendes/PAW-27B-GGUF

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 lackonendes/PAW-27B-GGUF
# Run inference directly in the terminal:
./llama-cli -hf lackonendes/PAW-27B-GGUF

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 lackonendes/PAW-27B-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lackonendes/PAW-27B-GGUF

Use Docker

docker model run hf.co/lackonendes/PAW-27B-GGUF

LM Studio
Jan
Ollama
How to use lackonendes/PAW-27B-GGUF with Ollama:
```
ollama run hf.co/lackonendes/PAW-27B-GGUF
```
Unsloth Desktop

How to use lackonendes/PAW-27B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lackonendes/PAW-27B-GGUF

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": "lackonendes/PAW-27B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lackonendes/PAW-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/lackonendes/PAW-27B-GGUF
```

Lemonade

How to use lackonendes/PAW-27B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lackonendes/PAW-27B-GGUF

Run and chat with the model

lemonade run user.PAW-27B-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use lackonendes/PAW-27B-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 lackonendes/PAW-27B-GGUF

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 lackonendes/PAW-27B-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lackonendes/PAW-27B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lackonendes/PAW-27B-GGUF

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 "lackonendes/PAW-27B-GGUF" \
  --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"

PAW-27B

A ~2.17 bpw trellis-coded quantization of Qwen/Qwen3.8-27B that runs on one 24 GB GPU with a 256k context at 38–78 tok/s.


size	7.814 GB (this file: `PAW-27B.gguf`)
context	262,144 tokens on a single RTX 3090
speed	78.4 tok/s short · 47.8 tok/s at 191k code context (MTP drafter)
code	87.2% HumanEval+, 75.9% MBPP+
general	58.6% MMLU-Pro, 94% GSM8K

Requirements — read this first

This is not a standard GGUF. It uses the PAW trellis format (paw-dense arch) and requires the llama-paw fork. Stock llama.cpp cannot read this model.

How it compares

Against two same-family IQ2XXS GGUFs, measured by us on the same machine with byte-identical harnesses:

	size	MMLU-Pro (500)	GSM8K (100)	HumanEval+	MBPP+	IFBench-64 strict
PAW-27B	7.814 GB	58.6%	94%	87.2%	75.9%	23.44%
Unsloth IQ2XXS	7.266 GB	46.2%	93%	84.1%	72.8%	14.06%
AtomicChat AD-IQ2XXS	8.977 GB	53.0%	94%	73.8%	71.7%	20.31%

PAW-27B leads MMLU-Pro, HumanEval+, MBPP+ and strict IFBench. Unsloth's file is 0.548 GB smaller and gives up 12.4 points of MMLU-Pro. AtomicChat is larger than PAW-27B and does not recover the coding gap.

Honest summary

These are peer comparisons, not retention numbers. No HumanEval, MBPP or GSM8K figure exists for Qwen/Qwen3.8-27B at any precision, so there is no published denominator to claim retention against on those axes, and we are not going to invent one. What the table shows is that at roughly the same file size this quantization is ahead of the two obvious alternatives — not how much of the unquantized parent survives.

The references that do exist for this parent are IFBench (79.5 unquantized, official Qwen) and LiveCodeBench v6 (90.3). The IFBench figure here is a 64-item defect sentinel, not the 300-item benchmark, so it is directional only and not comparable to the official 79.5.

Serving

See SERVING.md for the full configuration. Short version:

requires llama-paw, not stock llama.cpp
speculative decoding with the parent's own MTP head (--spec-type draft-mtp) — 22.7 → 78.4 tok/s, lossless
-ub 2048 is a hard ceiling at -c 262144, not a preference
KV at q8_0 is free; -fa on is required for it
for agent/tool use, do not send reasoning back across turns — see the loop limitation below

Limitations

Agent clients loop unless reasoning is dropped from history. The model copies its own prior <think> block verbatim and then repeats the action it went with. Serve with --no-reasoning-preserve and configure the client not to return reasoning_content. Details and measurements in SERVING.md.
Unbounded thinking returns empty answers. Use --reasoning-budget 2048, not -1.
Rare-glyph copy defect. The model cannot emit ➞ (U+279E) and aborts generation on prompts containing it; in this fork the server returns HTTP
1. Eight HumanEval prompts contain it and it reproduces deterministically under greedy decoding. This is a model defect, not a harness artifact, and the affected tasks are scored as failures in the numbers above.
No parent denominator on HumanEval/MBPP/GSM8K (see above).
IFBench here is a 64-item sentinel, not the full benchmark.
Long-context quality is unmeasured; only speed and footprint were measured at 191k–256k.

Integrity

sha256 f5ec4b409de07f43bbe7bb5d9b3215181c53f5a26876821f732839a2ea3ab8cf  PAW-27B.gguf

License

Apache 2.0, inherited from the base model Qwen/Qwen3.8-27B.

Downloads last month: 14

GGUF

Model size

6B params

Architecture

paw-dense

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for lackonendes/PAW-27B-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(915)

this model