Instructions to use Rahspide/MNN-Pocket-0.3B-RU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rahspide/MNN-Pocket-0.3B-RU with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Rahspide/MNN-Pocket-0.3B-RU")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rahspide/MNN-Pocket-0.3B-RU")
model = AutoModelForCausalLM.from_pretrained("Rahspide/MNN-Pocket-0.3B-RU", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Rahspide/MNN-Pocket-0.3B-RU 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 Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rahspide/MNN-Pocket-0.3B-RU: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 Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M

Use Docker

docker model run hf.co/Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Rahspide/MNN-Pocket-0.3B-RU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rahspide/MNN-Pocket-0.3B-RU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rahspide/MNN-Pocket-0.3B-RU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M

SGLang

How to use Rahspide/MNN-Pocket-0.3B-RU with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Rahspide/MNN-Pocket-0.3B-RU" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rahspide/MNN-Pocket-0.3B-RU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Rahspide/MNN-Pocket-0.3B-RU" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rahspide/MNN-Pocket-0.3B-RU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Rahspide/MNN-Pocket-0.3B-RU with Ollama:
```
ollama run hf.co/Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M
```
Unsloth Desktop

How to use Rahspide/MNN-Pocket-0.3B-RU with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU: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": "Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Rahspide/MNN-Pocket-0.3B-RU with Docker Model Runner:
```
docker model run hf.co/Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M
```

Lemonade

How to use Rahspide/MNN-Pocket-0.3B-RU with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M

Run and chat with the model

lemonade run user.MNN-Pocket-0.3B-RU-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Rahspide/MNN-Pocket-0.3B-RU with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU: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 Rahspide/MNN-Pocket-0.3B-RU:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Rahspide/MNN-Pocket-0.3B-RU with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU: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 "Rahspide/MNN-Pocket-0.3B-RU: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"

Rahspide commited on 3 days ago

Commit

52a9acb

verified ·

1 Parent(s): f5fc8a5

docs: MNN INT4 build, run instructions, release v1.1

Browse files

Files changed (1) hide show

README.md +14 -1

README.md CHANGED Viewed

@@ -161,6 +161,7 @@ used, so the resulting weights stay publishable.
 |---|---|---|---|
 | Q8_0 | 310 MB | [`MNN-Pocket-0.3B-RU-Q8_0.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU/blob/main/gguf/MNN-Pocket-0.3B-RU-Q8_0.gguf) | near-lossless, for desktop |
 | Q4_K_M | 223 MB | [`MNN-Pocket-0.3B-RU-Q4_K_M.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU/blob/main/gguf/MNN-Pocket-0.3B-RU-Q4_K_M.gguf) | the size to ship on a phone |
 Both files sit under `gguf/` with the quant tag in the name, which is what llama.cpp matches on:
@@ -178,6 +179,17 @@ Converted with llama.cpp `convert_hf_to_gguf.py` (f16) and quantised with `llama
 Phone figures will be several times lower; these are desktop-CPU numbers.
 Two conversion quirks, both already fixed in this repository's `tokenizer_config.json`.
 - the base pre-tokenizer does not hash-match in current llama.cpp, so the Qwen pre-tokenizer has to be pinned
@@ -235,13 +247,14 @@ deliberate trade: Russian is the target, English and Chinese are kept from degra
 | **v1** | Russian continuation model — this run | **released** |
 | **v2** | Russian assistant: SFT on ChatML on top of v1 — [released](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat) | **released** |
 | **v3** | Tokenizer extension measured: +8,192 Cyrillic merges give ×1.49 more Russian characters per token, +16,384 give ×1.63. `model_ext` (73,728 rows, child-mean init) is built; needs a 100–200 M token CPT to pay for itself | measured, CPT pending |
-| **v4** | Quantised builds for devices: GGUF Q8_0 / Q4_K_M shipped; MNN INT4 with device-side tok/s still open | partially done |
 ## Releases
 | Date | Version | What changed |
 |---|---|---|
 | 2026-11-10 | **v1.0** | 1.2 B-token continued pretraining released: bf16 weights, GGUF Q8_0 and Q4_K_M, measured ru/en/zh bits-per-char |
 | 2026-11-10 | v2.0 (sister) | Assistant checkpoint released: 50 M-token SFT on top of v1, weights and GGUF |
 ## Licence and attribution

 |---|---|---|---|
 | Q8_0 | 310 MB | [`MNN-Pocket-0.3B-RU-Q8_0.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU/blob/main/gguf/MNN-Pocket-0.3B-RU-Q8_0.gguf) | near-lossless, for desktop |
 | Q4_K_M | 223 MB | [`MNN-Pocket-0.3B-RU-Q4_K_M.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU/blob/main/gguf/MNN-Pocket-0.3B-RU-Q4_K_M.gguf) | the size to ship on a phone |
+| MNN INT4 | 165 MB | [mnn/MNN-Pocket-0.3B-RU-INT4](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU/tree/main/mnn/MNN-Pocket-0.3B-RU-INT4) | MNN runtime, Android |
 Both files sit under `gguf/` with the quant tag in the name, which is what llama.cpp matches on:
 Phone figures will be several times lower; these are desktop-CPU numbers.
+The MNN build runs through MNN's own runtime. Build `llm_demo` from the MNN repository with
+`-DMNN_BUILD_LLM=ON`, then point it at the folder:
+```bash
+cd mnn/MNN-Pocket-0.3B-RU-INT4 && llm_demo config.json prompt.txt
+```
+165 MB on disk, ~354 tok/s prefill and ~77 tok/s decode on 12 CPU threads here. `llm_config.json` carries no
+chat template on purpose: this checkpoint continues the prompt, so the runtime should not wrap it in a dialogue
+format.
 Two conversion quirks, both already fixed in this repository's `tokenizer_config.json`.
 - the base pre-tokenizer does not hash-match in current llama.cpp, so the Qwen pre-tokenizer has to be pinned
 | **v1** | Russian continuation model — this run | **released** |
 | **v2** | Russian assistant: SFT on ChatML on top of v1 — [released](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat) | **released** |
 | **v3** | Tokenizer extension measured: +8,192 Cyrillic merges give ×1.49 more Russian characters per token, +16,384 give ×1.63. `model_ext` (73,728 rows, child-mean init) is built; needs a 100–200 M token CPT to pay for itself | measured, CPT pending |
+| **v4** | Quantised builds for devices: GGUF Q8_0 / Q4_K_M and MNN INT4 shipped; phone-side tok/s still open | desktop done, phone pending |
 ## Releases
 | Date | Version | What changed |
 |---|---|---|
 | 2026-11-10 | **v1.0** | 1.2 B-token continued pretraining released: bf16 weights, GGUF Q8_0 and Q4_K_M, measured ru/en/zh bits-per-char |
+| 2026-11-11 | v1.1 | MNN INT4 build for the MNN runtime: 165 MB, ~77 tok/s decode on 12 CPU threads |
 | 2026-11-10 | v2.0 (sister) | Assistant checkpoint released: 50 M-token SFT on top of v1, weights and GGUF |
 ## Licence and attribution