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

Libraries

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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-Chat")
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-Chat")
model = AutoModelForCausalLM.from_pretrained("Rahspide/MNN-Pocket-0.3B-RU-Chat", 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-Chat 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-Chat:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat: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-Chat:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat: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-Chat:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Use Docker

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

Llama new
LM Studio
Jan

vLLM

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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-Chat"
# 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-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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-Chat" \
    --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-Chat",
		"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-Chat" \
        --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-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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-Chat: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-Chat:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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-Chat: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-Chat:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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-Chat: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-Chat: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"

MNN-Pocket-0.3B-RU-Chat / README.md

Rahspide

docs: drop forward-looking notes, keep released facts only

b9bc2eb verified about 14 hours ago

preview code

Raw History Blame Contribute Delete

9.3 kB

---
language:
- ru
- en
license: apache-2.0
base_model: Rahspide/MNN-Pocket-0.3B-RU
library_name: transformers
pipeline_tag: text-generation
datasets:
- IlyaGusev/saiga_scored
- HuggingFaceH4/ultrachat_200k
tags:
- russian
- chat
- assistant
- on-device
- mnn
- qwen3
- gguf
- work-in-progress
---
![MNN-Pocket-0.3B-RU-Chat — a Russian assistant in 0.3B](assets/cover_chat.png)

![params](https://img.shields.io/badge/params-361M-E2543F?style=flat-square)
![sft](https://img.shields.io/badge/sft-50M%20tokens-5FD3B4?style=flat-square)
![data](https://img.shields.io/badge/data-18.8M%20ru%20%2B%206M%20en-6FA8FF?style=flat-square)
![gguf](https://img.shields.io/badge/gguf-Q8__0%20%C2%B7%20Q4__K__M-E2543F?style=flat-square)
![license](https://img.shields.io/badge/license-apache--2.0-8B95A4?style=flat-square)
![status](https://img.shields.io/badge/status-v1%20released-5FD3B4?style=flat-square)

> **Status: v1 released.** Instruction-tuned on 50 M tokens (18.8 M Russian + 6 M English replay) on one Kaggle
> T4 in ~6.5 h. Weights and GGUF builds are in this repository.

Russian instruction-following assistant, built by SFT on top of
[`Rahspide/MNN-Pocket-0.3B-RU`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU). It answers instead of
continuing; that dialogue shape is what 50 M tokens of SFT bought.

## Two models, two jobs

![One base, two jobs](assets/two_jobs_chat.png)

| | Sister — `MNN-Pocket-0.3B-RU` | This model — `MNN-Pocket-0.3B-RU-Chat` |
|---|---|---|
| Job | continue text | follow instructions |
| Input | a prefix, often mid-sentence | a system + user message |
| Output | the plausible continuation | an answer |
| Trained with | continued pretraining on 1.2 B tokens of raw text | instruction tuning on top of that model |
| Choose it for | keyboard suggestions, autocomplete, prefix completion | chat, Q&A, short rewrites |
| Do not choose it for | assistant behaviour: it will continue your question instead of answering it | autocomplete: it will answer instead of continuing |

The two tasks reward opposite behaviour. Trained on both jobs, one checkpoint does each badly: it answers when
it should continue, and continues when it should answer.

## Why start from the Russian continuation model

The base `MNN-Pocket-0.3B` is bilingual zh/en and has essentially no Russian; a direct SFT of the official
instruct model would fight both problems at once (new language and new format). Starting from the continuation
model means Russian is already paid for, and SFT only has to teach the dialogue shape.

## Recipe (as run)

- Start point: `Rahspide/MNN-Pocket-0.3B-RU` (step 36,621).
- Chat template: the model's own ChatML (`<|im_start|>` / `<|im_end|>`), untouched.
- Loss only on assistant tokens; system and user turns are masked context.
- Multi-turn dialogue kept as one example; packing with explicit boundaries.
- One run at 50 M tokens (1,525 optimizer steps, 32 k tokens each), checkpoints every 300 steps.
- 85 / 15 Russian-to-English sampling per micro-batch; the English share keeps bilingual instruction following.
- lr 1e-4, cosine, 5% warmup, full fine-tuning, fp16 autocast on T4 with fp32 master weights.
- ~6.5 h on one Kaggle T4.

## Data (as used)

![Training mix](assets/mix.png)

| Dataset | Role | Licence |
|---|---|---|
| [`IlyaGusev/saiga_scored`](https://huggingface.co/datasets/IlyaGusev/saiga_scored) | core Russian instructions, 18.8 M tokens / 23,518 dialogues | see dataset card |
| [`HuggingFaceH4/ultrachat_200k`](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) | English replay, 6.0 M tokens / 5,181 dialogues | MIT |

Filters applied to `saiga_scored`: Russian only, dropped rows flagged `is_bad_by_regex`, 80–6,000 characters per
dialogue, 2–8 turns. Roles `bot` / `gpt` are normalised to `assistant`; empty turns are dropped.

## Quality spot-check

Greedy generation, Q4_K_M, CPU:

| Prompt | Answer |
|---|---|
| «Объясни в двух предложениях, что такое инфляция.» | «Инфляция — это процесс роста цен на товары и услуги в стране или за ее пределами. Этот процесс может привести к у…» |
| «Напиши короткое поздравление с днём рождения коллеге.» | «Дорогой [Имя], С днём рождения! Желаю, чтобы ваша работа была не только эффективной, но и приятной для глаз…» |
| «Привет! Как дела?» | repeats the question — a known weak spot of 0.3 B on very short turns |

The model answers instead of continuing the prompt. That is all this table proves.

## Builds

![GGUF sizes](assets/sizes.png)

| Build | Size | Download | Note |
|---|---|---|---|
| Q8_0 | 310 MB | [`MNN-Pocket-0.3B-RU-Chat-Q8_0.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/gguf/MNN-Pocket-0.3B-RU-Chat-Q8_0.gguf) | near-lossless |
| Q4_K_M | 223 MB | [`MNN-Pocket-0.3B-RU-Chat-Q4_K_M.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/gguf/MNN-Pocket-0.3B-RU-Chat-Q4_K_M.gguf) | phone size |
| MNN INT4 | 165 MB | [mnn/MNN-Pocket-0.3B-RU-Chat-INT4](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/tree/main/mnn/MNN-Pocket-0.3B-RU-Chat-INT4) | Android, MNN runtime |
```bash
llama-cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M --jinja -p "Объясни, что такое инфляция" -n 60
```
The MNN build runs on MNN's runtime (`llm_demo`, built with `-DMNN_BUILD_LLM=ON`). Its `llm_config.json` keeps
the ChatML template, so it answers out of the box:
```bash
cd mnn/MNN-Pocket-0.3B-RU-Chat-INT4 && llm_demo config.json prompt.txt
```
165 MB on disk, ~497 tok/s prefill and ~80 tok/s decode on 12 CPU threads. The answer is coherent Russian; the
INT4 weights cost some precision against Q8_0, as expected.
**~123 tok/s generation on Q4_K_M, ~102 tok/s on Q8_0** (16-thread x86 CPU, no GPU). Apply the model's own ChatML
template (`--jinja` in llama.cpp, `apply_chat_template` in transformers). Without it the model continues text
instead of answering and behaves like its sister.
## Reproduce
```bash
# chat smoke test through the model's own template
python bench/chat_smoke.py --model Rahspide/MNN-Pocket-0.3B-RU-Chat --cpu
# throughput of the quantised build
LLAMA_CLI=/path/to/llama-cli bash bench/bench_cpu.sh gguf/MNN-Pocket-0.3B-RU-Chat-Q4_K_M.gguf --chat
```
`bench/chat_smoke.py` applies the chat template from `tokenizer_config.json`, generates greedily and asserts that
the answer does not echo the prompt, which is a cheap check that the template and the checkpoint still match.
`bench/bench_cpu.sh --chat` wraps the prompt in ChatML before timing, so the numbers are comparable with the
table above.

## Evaluation

60 held-out Russian prompts from the `saiga_scored` validation slice, greedy decoding, the model's own template:

| Automatic check | Result |
|---|---|
| answers in Russian (>50% Cyrillic) | 57 / 60 |
| mean Cyrillic share of letters | 0.93 |
| empty answers | 0 |
| echoes the prompt | 2 |
| mean answer length, words | 26.1 |
| distinct-2 (higher = less repetition) | 0.90 |

The sheet with all 60 prompts and answers is in
[`review/blind_sheet.md`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/review/blind_sheet.md).

A comparison against `taobao-mnn/MNN-Pocket-0.3B` was attempted on the same prompts and dropped. That checkpoint
degenerates on Russian input, repeating the prompt in bold markdown fragments:

```
Q: Как стать популярным в яндекс дзен?
A: Конечный откорт: **"Популярный в яндекс дзен"** — это **не** в яндекс (в яндекс) — **в яндекс** — **в яндекс** — …
```

So it is not a baseline.

## Limitations

- 0.36 B parameters: short answers, weak facts, no reliable multi-step reasoning.
- Russian SFT data is mostly machine-translated or model-generated; style is flatter than human chat.
- The sister's tokenizer cost applies here too: about 3.3 tokens per Russian word, so ~3× more decode steps per
  Russian sentence than for English. The vocabulary is byte-level, so rare and uppercase Cyrillic letters can
  end up split across tokens; a streaming decoder has to buffer partial UTF-8 sequences.
- Not a coding model, not a tool-calling model, no long-context dialogue.
- English answers are thinner than Russian ones. Replay keeps the ability alive; it does not polish it.

## Releases

| Date | Version | What changed |
|---|---|---|
| 2026-11-10 | **v1.0** | Assistant released: 50 M-token SFT (18.8 M ru + 6 M en), bf16 weights, GGUF Q8_0 / Q4_K_M, ChatML smoke test passing |
| 2026-11-11 | v1.1 | MNN INT4 build for Android: 165 MB, ChatML template included, ~80 tok/s decode |
| 2026-11-10 | v1.0 (sister) | Continuation checkpoint released: 1.2 B-token CPT, same base |
## Licence and attribution
Weights: Apache-2.0, inherited through `MNN-Pocket-0.3B-RU` from `taobao-mnn/MNN-Pocket-0.3B-Base`.
```bibtex
@misc{mnn_pocket_03b,
  title  = {MNN-Pocket-0.3B},
  author = {Taobao MNN team},
  year   = {2026},
  url    = {https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B}
}
```

	---
	language:
	- ru
	- en
	license: apache-2.0
	base_model: Rahspide/MNN-Pocket-0.3B-RU
	library_name: transformers
	pipeline_tag: text-generation
	datasets:
	- IlyaGusev/saiga_scored
	- HuggingFaceH4/ultrachat_200k
	tags:
	- russian
	- chat
	- assistant
	- on-device
	- mnn
	- qwen3
	- gguf
	- work-in-progress
	---

	![MNN-Pocket-0.3B-RU-Chat — a Russian assistant in 0.3B](assets/cover_chat.png)

	![params](https://img.shields.io/badge/params-361M-E2543F?style=flat-square)
	![sft](https://img.shields.io/badge/sft-50M%20tokens-5FD3B4?style=flat-square)
	![data](https://img.shields.io/badge/data-18.8M%20ru%20%2B%206M%20en-6FA8FF?style=flat-square)
	![gguf](https://img.shields.io/badge/gguf-Q8__0%20%C2%B7%20Q4__K__M-E2543F?style=flat-square)
	![license](https://img.shields.io/badge/license-apache--2.0-8B95A4?style=flat-square)
	![status](https://img.shields.io/badge/status-v1%20released-5FD3B4?style=flat-square)

	> Status: v1 released. Instruction-tuned on 50 M tokens (18.8 M Russian + 6 M English replay) on one Kaggle
	> T4 in ~6.5 h. Weights and GGUF builds are in this repository.

	Russian instruction-following assistant, built by SFT on top of
	[`Rahspide/MNN-Pocket-0.3B-RU`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU). It answers instead of
	continuing; that dialogue shape is what 50 M tokens of SFT bought.

	## Two models, two jobs

	![One base, two jobs](assets/two_jobs_chat.png)

	\| \| Sister — `MNN-Pocket-0.3B-RU` \| This model — `MNN-Pocket-0.3B-RU-Chat` \|
	\|---\|---\|---\|
	\| Job \| continue text \| follow instructions \|
	\| Input \| a prefix, often mid-sentence \| a system + user message \|
	\| Output \| the plausible continuation \| an answer \|
	\| Trained with \| continued pretraining on 1.2 B tokens of raw text \| instruction tuning on top of that model \|
	\| Choose it for \| keyboard suggestions, autocomplete, prefix completion \| chat, Q&A, short rewrites \|
	\| Do not choose it for \| assistant behaviour: it will continue your question instead of answering it \| autocomplete: it will answer instead of continuing \|

	The two tasks reward opposite behaviour. Trained on both jobs, one checkpoint does each badly: it answers when
	it should continue, and continues when it should answer.

	## Why start from the Russian continuation model

	The base `MNN-Pocket-0.3B` is bilingual zh/en and has essentially no Russian; a direct SFT of the official
	instruct model would fight both problems at once (new language and new format). Starting from the continuation
	model means Russian is already paid for, and SFT only has to teach the dialogue shape.

	## Recipe (as run)

	- Start point: `Rahspide/MNN-Pocket-0.3B-RU` (step 36,621).
	- Chat template: the model's own ChatML (`<\|im_start\|>` / `<\|im_end\|>`), untouched.
	- Loss only on assistant tokens; system and user turns are masked context.
	- Multi-turn dialogue kept as one example; packing with explicit boundaries.
	- One run at 50 M tokens (1,525 optimizer steps, 32 k tokens each), checkpoints every 300 steps.
	- 85 / 15 Russian-to-English sampling per micro-batch; the English share keeps bilingual instruction following.
	- lr 1e-4, cosine, 5% warmup, full fine-tuning, fp16 autocast on T4 with fp32 master weights.
	- ~6.5 h on one Kaggle T4.

	## Data (as used)

	![Training mix](assets/mix.png)

	\| Dataset \| Role \| Licence \|
	\|---\|---\|---\|
	\| [`IlyaGusev/saiga_scored`](https://huggingface.co/datasets/IlyaGusev/saiga_scored) \| core Russian instructions, 18.8 M tokens / 23,518 dialogues \| see dataset card \|
	\| [`HuggingFaceH4/ultrachat_200k`](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) \| English replay, 6.0 M tokens / 5,181 dialogues \| MIT \|

	Filters applied to `saiga_scored`: Russian only, dropped rows flagged `is_bad_by_regex`, 80–6,000 characters per
	dialogue, 2–8 turns. Roles `bot` / `gpt` are normalised to `assistant`; empty turns are dropped.

	## Quality spot-check

	Greedy generation, Q4_K_M, CPU:

	\| Prompt \| Answer \|
	\|---\|---\|
	\| «Объясни в двух предложениях, что такое инфляция.» \| «Инфляция — это процесс роста цен на товары и услуги в стране или за ее пределами. Этот процесс может привести к у…» \|
	\| «Напиши короткое поздравление с днём рождения коллеге.» \| «Дорогой [Имя], С днём рождения! Желаю, чтобы ваша работа была не только эффективной, но и приятной для глаз…» \|
	\| «Привет! Как дела?» \| repeats the question — a known weak spot of 0.3 B on very short turns \|

	The model answers instead of continuing the prompt. That is all this table proves.

	## Builds

	![GGUF sizes](assets/sizes.png)

	\| Build \| Size \| Download \| Note \|
	\|---\|---\|---\|---\|
	\| Q8_0 \| 310 MB \| [`MNN-Pocket-0.3B-RU-Chat-Q8_0.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/gguf/MNN-Pocket-0.3B-RU-Chat-Q8_0.gguf) \| near-lossless \|
	\| Q4_K_M \| 223 MB \| [`MNN-Pocket-0.3B-RU-Chat-Q4_K_M.gguf`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/gguf/MNN-Pocket-0.3B-RU-Chat-Q4_K_M.gguf) \| phone size \|
	\| MNN INT4 \| 165 MB \| [mnn/MNN-Pocket-0.3B-RU-Chat-INT4](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/tree/main/mnn/MNN-Pocket-0.3B-RU-Chat-INT4) \| Android, MNN runtime \|

	```bash
	llama-cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M --jinja -p "Объясни, что такое инфляция" -n 60
	```

	The MNN build runs on MNN's runtime (`llm_demo`, built with `-DMNN_BUILD_LLM=ON`). Its `llm_config.json` keeps
	the ChatML template, so it answers out of the box:

	```bash
	cd mnn/MNN-Pocket-0.3B-RU-Chat-INT4 && llm_demo config.json prompt.txt
	```

	165 MB on disk, ~497 tok/s prefill and ~80 tok/s decode on 12 CPU threads. The answer is coherent Russian; the
	INT4 weights cost some precision against Q8_0, as expected.

	~123 tok/s generation on Q4_K_M, ~102 tok/s on Q8_0 (16-thread x86 CPU, no GPU). Apply the model's own ChatML
	template (`--jinja` in llama.cpp, `apply_chat_template` in transformers). Without it the model continues text
	instead of answering and behaves like its sister.

	## Reproduce

	```bash
	# chat smoke test through the model's own template
	python bench/chat_smoke.py --model Rahspide/MNN-Pocket-0.3B-RU-Chat --cpu

	# throughput of the quantised build
	LLAMA_CLI=/path/to/llama-cli bash bench/bench_cpu.sh gguf/MNN-Pocket-0.3B-RU-Chat-Q4_K_M.gguf --chat
	```

	`bench/chat_smoke.py` applies the chat template from `tokenizer_config.json`, generates greedily and asserts that
	the answer does not echo the prompt, which is a cheap check that the template and the checkpoint still match.
	`bench/bench_cpu.sh --chat` wraps the prompt in ChatML before timing, so the numbers are comparable with the
	table above.

	## Evaluation

	60 held-out Russian prompts from the `saiga_scored` validation slice, greedy decoding, the model's own template:

	\| Automatic check \| Result \|
	\|---\|---\|
	\| answers in Russian (>50% Cyrillic) \| 57 / 60 \|
	\| mean Cyrillic share of letters \| 0.93 \|
	\| empty answers \| 0 \|
	\| echoes the prompt \| 2 \|
	\| mean answer length, words \| 26.1 \|
	\| distinct-2 (higher = less repetition) \| 0.90 \|

	The sheet with all 60 prompts and answers is in
	[`review/blind_sheet.md`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/review/blind_sheet.md).

	A comparison against `taobao-mnn/MNN-Pocket-0.3B` was attempted on the same prompts and dropped. That checkpoint
	degenerates on Russian input, repeating the prompt in bold markdown fragments:

	```
	Q: Как стать популярным в яндекс дзен?
	A: Конечный откорт: "Популярный в яндекс дзен" — это не в яндекс (в яндекс) — в яндекс — в яндекс — …
	```

	So it is not a baseline.

	## Limitations

	- 0.36 B parameters: short answers, weak facts, no reliable multi-step reasoning.
	- Russian SFT data is mostly machine-translated or model-generated; style is flatter than human chat.
	- The sister's tokenizer cost applies here too: about 3.3 tokens per Russian word, so ~3× more decode steps per
	Russian sentence than for English. The vocabulary is byte-level, so rare and uppercase Cyrillic letters can
	end up split across tokens; a streaming decoder has to buffer partial UTF-8 sequences.
	- Not a coding model, not a tool-calling model, no long-context dialogue.
	- English answers are thinner than Russian ones. Replay keeps the ability alive; it does not polish it.

	## Releases

	\| Date \| Version \| What changed \|
	\|---\|---\|---\|
	\| 2026-11-10 \| v1.0 \| Assistant released: 50 M-token SFT (18.8 M ru + 6 M en), bf16 weights, GGUF Q8_0 / Q4_K_M, ChatML smoke test passing \|
	\| 2026-11-11 \| v1.1 \| MNN INT4 build for Android: 165 MB, ChatML template included, ~80 tok/s decode \|
	\| 2026-11-10 \| v1.0 (sister) \| Continuation checkpoint released: 1.2 B-token CPT, same base \|

	## Licence and attribution

	Weights: Apache-2.0, inherited through `MNN-Pocket-0.3B-RU` from `taobao-mnn/MNN-Pocket-0.3B-Base`.

	```bibtex
	@misc{mnn_pocket_03b,
	title = {MNN-Pocket-0.3B},
	author = {Taobao MNN team},
	year = {2026},
	url = {https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B}
	}
	```