Instructions to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use samuelcardillo/Carnice-MoE-35B-A3B-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 samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

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 samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

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 samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

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": "samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M
```

Lemonade

How to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Carnice-MoE-35B-A3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use samuelcardillo/Carnice-MoE-35B-A3B-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 samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

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 samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use samuelcardillo/Carnice-MoE-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M

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 "samuelcardillo/Carnice-MoE-35B-A3B-GGUF:Q4_K_M" \
  --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"

Carnice-MoE-35B-A3B-GGUF / README.md

samuelcardillo

Add model card

a8ad858 verified 6 months ago

preview code

Raw History Blame Contribute Delete

4.03 kB

	---
	language:
	- en
	license: apache-2.0
	tags:
	- qwen3.5
	- moe
	- hermes
	- agentic
	- tool-calling
	- qlora
	- unsloth
	- carnice
	base_model: Qwen/Qwen3.5-35B-A3B
	datasets:
	- bespokelabs/Bespoke-Stratos-17k
	- AI-MO/NuminaMath-CoT
	- kai-os/carnice-glm5-hermes-traces
	- open-thoughts/OpenThoughts-Agent-v1-SFT
	---

	# Carnice MoE 35B-A3B — Hermes-Focused Agentic Model (GGUF)

	QLoRA fine-tune of Qwen3.5-35B-A3B (MoE, 3B active parameters) optimized for agentic workflows and Hermes Agent runtime. Two-stage training adapted from [kai-os/Carnice-9b](https://huggingface.co/kai-os/Carnice-9b).

	## Credits

	Training methodology adapted from [kai-os/Carnice-9b](https://huggingface.co/kai-os/Carnice-9b) — same two-stage approach and datasets, applied to the larger MoE architecture. Key inspiration: training on actual Hermes Agent execution traces for native agentic behavior.

	## Available Quantizations

	\| Quantization \| Size \| BPW \| Min VRAM \|
	\|---\|---\|---\|---\|
	\| Q8_0 \| 35 GB \| 8.52 \| 1x 48GB GPU \|
	\| Q6_K \| 27 GB \| 6.58 \| 1x 32GB GPU \|
	\| Q5_K_M \| 24 GB \| 5.70 \| 1x 32GB GPU \|
	\| Q4_K_M \| 20 GB \| 4.87 \| 1x 24GB GPU \|
	\| MXFP4_MOE \| 19 GB \| 4.39 \| 1x 24GB GPU \|

	For BF16 safetensors, see [samuelcardillo/Carnice-MoE-35B-A3B](https://huggingface.co/samuelcardillo/Carnice-MoE-35B-A3B).

	## Model Details

	\| Property \| Value \|
	\|---\|---\|
	\| Base Model \| [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B) \|
	\| Architecture \| Mixture of Experts (MoE) \|
	\| Total Parameters \| ~35B \|
	\| Active Parameters \| ~3B per token \|

	## What Makes This Different

	Unlike generic reasoning distillation, this model was trained on actual Hermes Agent execution traces — real conversations where an AI agent:
	- Executes terminal commands and processes output
	- Performs file editing operations
	- Chains multi-step tool calls with results feeding back
	- Uses browser-assisted workflows
	- Makes decisions based on environmental feedback

	This teaches the model the exact conversation patterns Hermes expects, rather than just generic reasoning.

	## Training Details

	### Two-Stage Approach

	Stage A — Reasoning Repair (1 epoch)
	- Strengthens base model reasoning before agent-specific training
	- Loss: 0.4159

	\| Dataset \| Examples \|
	\|---\|---\|
	\| [bespokelabs/Bespoke-Stratos-17k](https://huggingface.co/datasets/bespokelabs/Bespoke-Stratos-17k) \| 16,710 \|
	\| [AI-MO/NuminaMath-CoT](https://huggingface.co/datasets/AI-MO/NuminaMath-CoT) \| 17,000 (capped) \|

	Stage B — Hermes Traces (2 epochs)
	- Agent-specific behavioral training on real execution traces
	- Loss: 0.3115

	\| Dataset \| Examples \|
	\|---\|---\|
	\| [kai-os/carnice-glm5-hermes-traces](https://huggingface.co/datasets/kai-os/carnice-glm5-hermes-traces) \| 1,627 (high quality) \|
	\| [open-thoughts/OpenThoughts-Agent-v1-SFT](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT) \| 15,209 \|

	### Training Configuration

	\| Parameter \| Stage A \| Stage B \|
	\|---\|---\|---\|
	\| LoRA Rank \| 64 \| 64 \|
	\| LoRA Alpha \| 64 \| 64 \|
	\| LoRA Targets \| q, k, v, o projections \| q, k, v, o projections \|
	\| Learning Rate \| 2e-5 (linear) \| 1e-5 (cosine) \|
	\| Epochs \| 1 \| 2 \|
	\| Effective Batch \| 12 \| 12 \|
	\| Context Length \| 4096 \| 4096 \|
	\| Precision \| 4-bit QLoRA + BF16 adapters \| Same \|
	\| GPU \| RTX PRO 6000 Blackwell (96GB) \| Same \|
	\| Total Training Time \| ~44 hours (both stages) \|

	### Trainable Parameters
	6,881,280 (0.02% of 35B total)

	## Usage with llama.cpp

	```bash
	llama-server \
	--model Carnice-MoE-35B-A3B-Q8_0.gguf \
	--n-gpu-layers -1 \
	--ctx-size 131072 \
	--host 0.0.0.0 --port 8082
	```

	## Acknowledgements

	- [kai-os](https://huggingface.co/kai-os) — Carnice training methodology and Hermes traces dataset
	- [open-thoughts](https://huggingface.co/open-thoughts) — Agent SFT dataset
	- [bespokelabs](https://huggingface.co/bespokelabs) — Bespoke-Stratos reasoning dataset
	- [Unsloth](https://unsloth.ai) — QLoRA training framework
	- [Qwen](https://huggingface.co/Qwen) — Base model