Instructions to use PollardWeights/Carnice-V3-27b-Pollard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use PollardWeights/Carnice-V3-27b-Pollard 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 PollardWeights/Carnice-V3-27b-Pollard:IQ3_S
# Run inference directly in the terminal:
llama cli -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S
# Run inference directly in the terminal:
llama cli -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

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 PollardWeights/Carnice-V3-27b-Pollard:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

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 PollardWeights/Carnice-V3-27b-Pollard:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

Use Docker

docker model run hf.co/PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

LM Studio
Jan

vLLM

How to use PollardWeights/Carnice-V3-27b-Pollard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PollardWeights/Carnice-V3-27b-Pollard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PollardWeights/Carnice-V3-27b-Pollard",
		"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/PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

Ollama
How to use PollardWeights/Carnice-V3-27b-Pollard with Ollama:
```
ollama run hf.co/PollardWeights/Carnice-V3-27b-Pollard:IQ3_S
```

Unsloth Studio

How to use PollardWeights/Carnice-V3-27b-Pollard 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 PollardWeights/Carnice-V3-27b-Pollard 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 PollardWeights/Carnice-V3-27b-Pollard to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PollardWeights/Carnice-V3-27b-Pollard to start chatting

How to use PollardWeights/Carnice-V3-27b-Pollard with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

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": "PollardWeights/Carnice-V3-27b-Pollard:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PollardWeights/Carnice-V3-27b-Pollard with Docker Model Runner:
```
docker model run hf.co/PollardWeights/Carnice-V3-27b-Pollard:IQ3_S
```

Lemonade

How to use PollardWeights/Carnice-V3-27b-Pollard with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

Run and chat with the model

lemonade run user.Carnice-V3-27b-Pollard-IQ3_S

List all available models

lemonade list

Hermes Agent

How to use PollardWeights/Carnice-V3-27b-Pollard with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

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 PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PollardWeights/Carnice-V3-27b-Pollard with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S

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 "PollardWeights/Carnice-V3-27b-Pollard:IQ3_S" \
  --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"

Pollard quantizations of Carnice-V3-27b by kai-os

Carnice on a Mac, not a 3090. Carnice-V3-27b is a 27B agent model (Qwen3.8-27B + a Hermes-agent SFT distilled from Qwen3.8-Max) that punches far above its size on agent tasks — built to fit a 3090 / 24 GB. Pollard sizes it to your box: the recommended build is ~12 GB and runs on a 16 GB Mac.

Built with Pollard Weights on a runtime with native qwen35 support.

Original model: https://huggingface.co/kai-os/Carnice-V3

Model details


Parameter count	27B (dense)
Architecture	`qwen35` (65 layers, 5120 hidden)
Context length	262,144 (256K)
Input support	text + image + video (multimodal)
Specialty	Hermes-agent, tool-use — "beats models 10× the size" on agent tasks
imatrix	yes — Qwen3.8-27B importance matrix (same base; transferable)
Source	Q8_0 (near-lossless; ~99.9% of bf16)

Which file should I choose?

~16 GB Mac / 12 GB VRAM → IQ3_S (12 GB). Runs the 27B where a 3090 was the bar. Recommended headline build.
~24 GB (a 3090) → IQ4_XS (~16 GB) — smaller than Carnice's own build, more fidelity. (coming)
~32 GB → Q6_K (~22 GB) — near-lossless. (coming)

Available files

file	quant	size	held-out PPL	M4 tok/s
Carnice-V3-27b-Pollard-IQ3_S.gguf	IQ3_S measured mix	12.08 GB	7.88	~6.9
mmproj-Carnice-V3-BF16.gguf	vision projector (f16, not quantized)	0.93 GB	—	—

(tok/s is a 16 GB Mac at IQ3 — bandwidth-bound with partial Metal offload; it's markedly faster on 24 GB+ with the whole model resident, and on any CUDA GPU.)

Prompt format

Carnice uses ChatML (Qwen3.5), with tool-use and agent formatting:

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Multimodal (vision + video)

Ship the mmproj alongside the model (it's kept at f16 — never quantize the projector) and run with llama.cpp's multimodal CLI/server:

llama-mtmd-cli -m Carnice-V3-27b-Pollard-IQ3_S.gguf \
  --mmproj mmproj-Carnice-V3-BF16.gguf --image photo.jpg -p "Describe this image."
# or serve vision:
llama-server -m Carnice-V3-27b-Pollard-IQ3_S.gguf --mmproj mmproj-Carnice-V3-BF16.gguf -ngl 99

Download

pip install -U "huggingface_hub[cli]"
hf download PollardWeights/Carnice-V3-27b-Pollard \
  --include "Carnice-V3-27b-Pollard-IQ3_S.gguf" "mmproj-Carnice-V3-BF16.gguf" --local-dir ./

How to run (text)

curl -LsSf https://llama.app/install.sh | sh
llama-server -hf PollardWeights/Carnice-V3-27b-Pollard:IQ3_S    # OpenAI API + web UI :8080
llama-cli   -m Carnice-V3-27b-Pollard-IQ3_S.gguf -ngl 99 -st -p "Plan a 3-step task."

Needs a recent llama.cpp with qwen35 support. Also runs in LM Studio, koboldcpp, Jan, etc. once they ship a new-enough llama.cpp.

Notes

License: Apache-2.0, inherited from Carnice-V3 / Qwen3.8-27B.
Requantized from Q8_0 (near-lossless source; an f16 source is marginally better, but for an IQ3/IQ4 target the difference is negligible).
imatrix is the base Qwen3.8-27B matrix (Carnice is a merged-LoRA fine-tune of the same base, so it transfers); imatrix-uncovered tensors are pinned to q6_K.
Quantized, not fine-tuned — same weights, sized to your machine.

Credits

Base model: kai-os/Carnice-V3 — Qwen3.8-27B
- Hermes-agent SFT (thanks to NousResearch, LambdaAPI, per the author).
Foundation: Qwen/Qwen3.8-27B.
Quantization runtime: llama.cpp.
Method + tooling: Pollard Weights — measure first, no claim before a number.

Downloads last month: -

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

3-bit

4-bit

Model tree for PollardWeights/Carnice-V3-27b-Pollard

Base model

Qwen/Qwen3.8-27B

Finetuned

kai-os/Carnice-V3

Quantized

(4)

this model