Instructions to use DRUPEs/CherryPit-1.1-2B-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 DRUPEs/CherryPit-1.1-2B-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 DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DRUPEs/CherryPit-1.1-2B-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 DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use DRUPEs/CherryPit-1.1-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DRUPEs/CherryPit-1.1-2B-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": "DRUPEs/CherryPit-1.1-2B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Ollama
How to use DRUPEs/CherryPit-1.1-2B-GGUF with Ollama:
```
ollama run hf.co/DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use DRUPEs/CherryPit-1.1-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DRUPEs/CherryPit-1.1-2B-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": "DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DRUPEs/CherryPit-1.1-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M
```

Lemonade

How to use DRUPEs/CherryPit-1.1-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CherryPit-1.1-2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use DRUPEs/CherryPit-1.1-2B-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 DRUPEs/CherryPit-1.1-2B-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 DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DRUPEs/CherryPit-1.1-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DRUPEs/CherryPit-1.1-2B-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 "DRUPEs/CherryPit-1.1-2B-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"

CherryPit-1.1-2B-GGUF

CherryPit-1.1-2B is the second release of CherryPit from DRUPEs (Dense Representation & Unified Parameter Encoding Systems), built on MiniCPM5-2B. It reasons much better inside a fixed thinking budget: with the same 8K thinking tokens it solves far more competition-math and coding problems than CherryPit-1.0, and it can now build React web apps from tests. Same size, architecture and speed as 1.0.

Results vs CherryPit-1.0

Both models were run on the same harness, items, prompts and seeds (bf16 weights in vLLM). "Thinking, 8K" means the model may think for up to 8,192 tokens before it answers; "–" = not measured for that model.

Benchmark	Setting	CherryPit-1.0	CherryPit-1.1	Δ
Math
AIME 2025	thinking, 8K, avg of 4	–	47.5	–
AIME 2026	thinking, 8K, avg of 4	–	56.7	–
HMMT Feb 2025	thinking, 8K, avg of 4	–	29.2	–
HMMT Feb 2026	thinking, 8K, avg of 4	–	27.3	–
AMC 2023	thinking, 8K, avg of 4	–	88.1	–
MATH-500	no thinking, greedy	78.2	87.8	+9.6
Coding
LiveCodeBench v6	thinking, 8K	29.1	46.3	+17.2
— hard problems	thinking, 8K, 80-problem probe	4.2	24.2	+20.0
LiveCodeBench v6	no thinking, avg of 4	31.7	31.0	−0.7
HumanEval+	no thinking, greedy	85.4	82.9	−2.5
MBPP+	no thinking, greedy	64.5	67.2	+2.7
Web development
WebApp1K-React	no thinking, 1,000 tasks	1.6	79.9	+78.3
FullStack Bench (web slice)	no thinking, 98 items x5	47.2	46.6	−0.6
Instruction following
IFEval	strict, prompt level	85.2	83.2	−2.0

Pooled over the 163 competition problems: 51.7. It also gets there with fewer tokens: on LiveCodeBench with thinking it uses 6,176 tokens per problem on average vs 7,454 for CherryPit-1.0.

Quantization

The Q4_K_M file was unpacked back to bf16 and re-run on the same harness, so this is what 4-bit costs. Thinking-mode coding is the most sensitive; if you have the memory, Q5_K_M or larger keeps more of it.

Benchmark	bf16	Q4_K_M	Δ
LiveCodeBench v6, thinking 8K	46.3	41.1	−5.2
LiveCodeBench v6, no thinking	31.0	29.6	−1.4
HumanEval+	82.9	84.8	+1.9
MBPP+	67.2	63.8	−3.4
MATH-500	87.8	84.8	−3.0
IFEval	83.2	81.9	−1.3

What's new in 1.1

Budget-aware reasoning: reinforcement learning under a fixed thinking budget, so the model reaches an answer inside 8K tokens instead of running out of room.
Ladder training on hard problems: the model starts from hints taken from its own long correct solutions, and the hints are removed step by step until it solves the problem on its own (math and code).
Knowing when to stop: once it has found the answer it commits to it instead of thinking on.
Web apps: React components written to pass a given set of tests (from the 1.1 WebDev preview).

Model Details

Developed by: DRUPEs
Model type: Causal language model
Parameters: ~2B
Base model: MiniCPM5-2B
Previous version: CherryPit-1.0-2B-GGUF
Architecture: Standard Llama
Context length: 128K tokens (131,072)
Tool calling: Supported (via the built-in chat template)
Language(s): English
License: Apache 2.0
Version: 1.1

How to Use

Which file should I pick? Start with Q4_K_M (1.56 GB). If you have the memory, Q6_K or Q8_0 are close to lossless. Avoid the Q2 files.

Ollama

ollama run hf.co/DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

LM Studio

Search for DRUPEs/CherryPit-1.1-2B-GGUF in the Discover tab and pick a quant.

llama.cpp

# chat in the terminal
llama-cli -hf DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

# OpenAI-compatible server on http://localhost:8080
llama-server -hf DRUPEs/CherryPit-1.1-2B-GGUF:Q4_K_M

Recommended sampling: temperature 1.0, top_p 0.95.

Thinking on or off

The chat template starts in thinking mode, which is best for hard math and code; give it 8K or more new tokens. For short, direct answers turn thinking off: in llama.cpp add --chat-template-kwargs '{"enable_thinking":false}'; in other apps use the "thinking" or "reasoning" toggle. With no system prompt the model introduces itself as CherryPit.

Files

File	Size
`CherryPit-1.1-2B-F16.gguf`	5.04 GB
`CherryPit-1.1-2B-Q8_0.gguf`	2.68 GB
`CherryPit-1.1-2B-Q6_K_L.gguf`	2.20 GB
`CherryPit-1.1-2B-Q6_K.gguf`	2.07 GB
`CherryPit-1.1-2B-Q5_K_M.gguf`	1.81 GB
`CherryPit-1.1-2B-Q4_K_L.gguf`	1.76 GB
`CherryPit-1.1-2B-Q4_K_M.gguf`	1.56 GB
`CherryPit-1.1-2B-Q4_K_S.gguf`	1.50 GB
`CherryPit-1.1-2B-IQ4_XS.gguf`	1.42 GB
`CherryPit-1.1-2B-Q3_K_L.gguf`	1.38 GB
`CherryPit-1.1-2B-Q2_K_L.gguf`	1.30 GB
`CherryPit-1.1-2B-Q3_K_M.gguf`	1.29 GB
`CherryPit-1.1-2B-IQ3_M.gguf`	1.23 GB
`CherryPit-1.1-2B-IQ3_XS.gguf`	1.15 GB
`CherryPit-1.1-2B-IQ2_M.gguf`	0.97 GB

All quants use an importance matrix computed at 4K context on CherryPit's own long reasoning traces plus general chat and code, which keeps thinking-mode quality far better than a short-answer calibration (Q4_K_M: 41.1 vs 36.0 on LiveCodeBench with thinking). _L = token embedding and output layer kept at Q8_0. The F16 file is full precision.

Limitations

It is a 2B model: it can be confidently wrong, so check answers that matter.
Instruction following (IFEval) and HumanEval+ are slightly below 1.0, see the table.
Tested in English only.

Downloads last month: 881

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for DRUPEs/CherryPit-1.1-2B-GGUF

Base model

openbmb/MiniCPM5-2B

Quantized

(130)

this model