Instructions to use UnimeType/Transliteration-2.0-9B-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 UnimeType/Transliteration-2.0-9B-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 UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf UnimeType/Transliteration-2.0-9B-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 UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf UnimeType/Transliteration-2.0-9B-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 UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use UnimeType/Transliteration-2.0-9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UnimeType/Transliteration-2.0-9B-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": "UnimeType/Transliteration-2.0-9B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M

Ollama
How to use UnimeType/Transliteration-2.0-9B-GGUF with Ollama:
```
ollama run hf.co/UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use UnimeType/Transliteration-2.0-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UnimeType/Transliteration-2.0-9B-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": "UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use UnimeType/Transliteration-2.0-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M
```

Lemonade

How to use UnimeType/Transliteration-2.0-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Transliteration-2.0-9B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use UnimeType/Transliteration-2.0-9B-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 UnimeType/Transliteration-2.0-9B-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 UnimeType/Transliteration-2.0-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use UnimeType/Transliteration-2.0-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UnimeType/Transliteration-2.0-9B-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 "UnimeType/Transliteration-2.0-9B-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"

UnimeType Transliteration 2.0 9B — v2.6 (12-Language Offline IME Engine · GGUF Q4_K_M & Q8_0)

Current Release: v2.6 (dataset_v5.1 · 12 Languages / 13 Modes + Blind-Typing Typo Recovery) · Protocol: unimetype-convert-short-v3 (0 system-prompt tokens, 100% drop-in compatible with all Transliteration-2.0 clients)

UnimeType gives you one keyboard for all your languages — no switching keyboards across apps or mid-sentence. Keep a clean ASCII layout for single-key shortcuts in Figma or Blender, LaTeX commands in Overleaf, WASD controls in games, Terminal/IDE workflows, and switching between Slack, Mail, WhatsApp, WeChat, or LINE, then convert romanized text in-place only when you want native script.

UnimeType Transliteration 2.0 9B (v2.6) is a deterministic on-device input-method transliteration engine fine-tuned from unquantized BF16 Qwen/Qwen3.5-9B. It converts romanized or ASCII-typed input across 12 languages (13 output modes) — Chinese Pinyin, Japanese Romaji (natural & kana), Hindi Hinglish, Arabic Arabizi, Russian, Greek, Vietnamese, Spanish, French, Portuguese, German, and Italian — while keeping inline English terms, @handles, URLs, code spans, file paths, numbers, and line breaks untouched.

🚀 Launch Interactive Playground Space → (Inspect multi-clause presets or run live in-browser WebAssembly inference)
⌨️ Download the UnimeType Keyboard App → (One keyboard across macOS, Windows, Linux, iOS, Android & ChromeOS — zero keyboard switching across apps or mid-sentence)
📖 Evaluation Methodology & Local LM Studio Setup Guide →

Official `v2.6` Model Family (`0.8B` · `4B` · `9B`)

Tier & Footprint	Apple Silicon (`MLX 6-bit`)	PyTorch / vLLM (`BF16 Safetensors`)	`llama.cpp` / LM Studio / Ollama (`GGUF`)
0.8B · Ultra-light mobile & browser WASM (`~0.5–0.7 GB`)	MLX 6-bit	BF16 Safetensors	GGUF Q4_K_M & Q8_0
4B · Balanced everyday desktop IME (`~2.6–3.5 GB`)	MLX 6-bit	BF16 Safetensors	GGUF Q4_K_M & Q8_0
9B · Flagship offline accuracy (`~5.6–7.4 GB`, beats cloud on Core-5)	MLX 6-bit	BF16 Safetensors	GGUF Q4_K_M & Q8_0 (this repo)

Included GGUF Quantizations

Filename	Quantization	Recommended Use
`Transliteration-2.0-9B-Convert-Q4_K_M.gguf`	`Q4_K_M` (4-bit k-quant)	Best speed / RAM balance for laptops, mobile runtimes, and WebAssembly
`Transliteration-2.0-9B-Convert-Q8_0.gguf`	`Q8_0` (8-bit near-lossless)	Maximum quantization fidelity for desktop LM Studio, `llama.cpp`, and Ollama

What's New in `v2.6`

12 Languages / 13 Output Modes with Zero System Prompt: Expands from 4 languages (zh, ja, hi, ar) to 12 languages (chinese, japanese natural & kana, hindi, arabic, russian, greek, vietnamese, spanish, french, portuguese, german, italian) using a single-line compact JSON user message and an empty system prompt (0 prompt-prefix overhead).
New 9B Flagship Offline Tier Surpasses Cloud on Core Benchmarks: Transliteration-2.0-9B reaches 92.09% strict accuracy on the 708-case v4-aligned suite (+1.27 pp ahead of DeepSeek V4.1 Flash with a ~2,800-token production system prompt) and 90.94% on Core-5 (+0.64 pp ahead of cloud), while matching cloud accuracy on Dogfood-30 (76.7%) and OOD-Unseen-20 probe repair (90.0%, 18/20).
Blind-Typing Adjacent-Key Typo Repair & Glossary Precision: Recovers realistic fast-typing transpositions (e.g., shujuuk → 数据库, yanchanghiu → 演唱会, yanuhuo → 验货), honors dynamic lexicon contact/brand entries without false-positive homophone hijacking, and cleanly emits UNIMETYPE_NO_ALTERNATIVE when closed-set reconvert alternatives are exhausted.
Unconditional Non-Thinking Chat Template: Ships with <|im_start|>assistant\n<think>\n\n</think>\n\n baked into chat_template.jinja across MLX, Safetensors, and GGUF so LM Studio, mlx-lm, and llama.cpp emit converted text on the very first token with zero reasoning-token latency.

Quickstart: `unimetype-convert-short-v3` Compact JSON Protocol

Usage Note: This checkpoint is a specialized IME conversion engine, not an open-ended chatbot. Send a compact JSON object as the user message with empty System Prompt and temperature: 0, or pair LM Studio / Ollama directly with the UnimeType Keyboard App for system-wide Caps Lock / Convert key replacement in any app.

Scenario (`1 Native Language + English`)	`user` Message JSON (`content`)	Direct `assistant` Output
Chinese + English (`zh`)	`{"operation":"convert","input":"qing xian zai staging huanjing pao yi bian suoyou unit test, queren API latency meiyou shenggao zhi hou, women zai anpai production deploy","enabled_languages":["chinese","english"],"primary_language":"chinese"}`	`请先在 staging 环境跑一遍所有 unit test, 确认 API latency 没有升高之后, 我们再安排 production deploy`
Japanese + English (`ja`)	`{"operation":"convert","input":"staging kankyou de atarashii API endpoint no dousa wo kakunin shite kara, mondai ga nakereba ban-gohan no ato ni production deploy shimasu","enabled_languages":["english","japanese"],"primary_language":"japanese","japanese_output_style":"natural"}`	`staging 環境で新しい API endpoint の動作を確認してから, 問題がなければ晩ご飯の後に production deploy します`
Hindi + English (`hi`)	`{"operation":"convert","input":"maine GitHub par naya PR open kar diya hai, aap ek baar code review kar lijiye, phir hum shaam ko staging server par deploy karenge","enabled_languages":["english","hindi"],"primary_language":"hindi"}`	`मैंने GitHub पर नया PR open कर दिया है, आप एक बार code review कर लीजिए, फिर हम शाम को staging server पर deploy करेंगे`
Arabic + English (`ar`)	`{"operation":"convert","input":"ana 7a2a3od fel office l7ad el sa3a 8 3ashan a5allas el deployment, law 3andak ay update eb3atli 3ala Slack aw WhatsApp","enabled_languages":["arabic","english"],"primary_language":"arabic"}`	`أنا هقعد في ال office لحد الساعة 8 عشان أخلص ال deployment, لو عندك أي update ابعتلي على Slack أو WhatsApp`
Russian + English (`ru`)	`{"operation":"convert","input":"pozhaluista prover novyi Docker build na staging pered tem kak my nachnem release","enabled_languages":["english","russian"],"primary_language":"russian"}`	`пожалуйста проверь новый Docker build на staging перед тем как мы начнем release`
German + English (`de`)	`{"operation":"convert","input":"koennen wir das API Gateway fuer den neuen Docker Container heute noch ueberpruefen","enabled_languages":["english","german"],"primary_language":"german"}`	`können wir das API Gateway für den neuen Docker Container heute noch überprüfen`

curl http://127.0.0.1:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "UnimeType/Transliteration-2.0-9B-GGUF",
    "temperature": 0,
    "max_tokens": 256,
    "messages": [
      {
        "role": "user",
        "content": "{\"operation\":\"convert\",\"input\":\"mingtian 3pm he @alex review auth-service de PR #412, ranhou deploy dao staging\",\"enabled_languages\":[\"chinese\",\"english\"],\"primary_language\":\"chinese\"}"
      }
    ]
  }'

Evaluation Benchmarks (`v2.6`)

1. Six-Suite Head-to-Head Benchmark: Offline `v2.6` (`0.8B / 4B / 9B`) vs. Cloud `DeepSeek V4.1 Flash`

All offline v2.6 models run with 0 system-prompt tokens (system_prompt = "", compact JSON input, temperature = 0), compared head-to-head against UnimeType's production cloud baseline (deepseek-v4.1-flash paired with the full ~2,800-token v30 production system prompt and boundary guards). Zero sentence or OOD probe overlap (0.00%) exists between training data and any of the 6 evaluation suites (1,975 held-out prompts total).

Model / Tier	System Prompt Overhead	`708` Shared (`v4`-Aligned)	Core-5 (`773` Cases)	12-Language / 13-Mode (`1,573` Cases)	`MST-Bench-520` (Exact / Tolerant)	`Dogfood-30` Real Pain Points (Exact / Tolerant)	Zero-Overlap `OOD-Unseen-20` (Exact / Tolerant / Probe Repair)
`DeepSeek V4.1 Flash` (Cloud Baseline)	~2,800 tok (`v30`)	90.82% (643/708)	90.30% (698/773)	93.20% (1466/1573)	73.46% / 74.81%	53.3% / 76.7% (23/30)	45% / 75% / 90% (18/20)
`Transliteration-2.0-0.8B` (`v2.6`)	0 tok (short JSON)	72.32% (512/708)	71.15% (550/773)	69.99% (1101/1573)	41.15% / 41.73%	36.7% / 36.7% (11/30)	25% / 25% / 45% (9/20)
`Transliteration-2.0-4B` (`v2.6`)	0 tok (short JSON)	89.12% (631/708)	87.45% (676/773)	88.11% (1386/1573)	63.27% / 63.85%	50.0% / 56.7% (17/30)	35% / 35% / 75% (15/20)
`Transliteration-2.0-9B` (`v2.6`)	0 tok (short JSON)	92.09% (`+1.27 pp` vs cloud)	90.94% (`+0.64 pp` vs cloud)	91.54% (1440/1573)	65.58% / 67.31%	73.3% / 76.7% (`= cloud`)	55% / 60% / 90% (18/20, `= cloud`)

Boundary Safety: Across all 520 noisy mixed-script inputs in MST-Bench-520, all three v2.6 offline models (0.8B, 4B, 9B) recorded 0 protected-span corruptions (URL, @handle, #issue, code, file paths, and version tags preserved verbatim) and 100% pass on closed-set reconvert exhaustion (UNIMETYPE_NO_ALTERNATIVE).

2. Per-Language Strict Accuracy Across All 12 Languages / 13 Modes (`1,573` Held-Out Cases)

Language / Output Mode	Cases	`DeepSeek V4.1 Flash` (Cloud)	`v2.6` `0.8B`	`v2.6` `4B`	`v2.6` `9B`
Chinese Pinyin (`chinese`)	261	88.1%	75.9%	91.2%	93.5%
Japanese Kanji-Kana (`japanese:natural`)	139	95.7%	60.4%	85.6%	87.0%
Japanese Kana-Only (`japanese:kana`)	100	90.0%	66.0%	75.0%	86.0%
Hindi Hinglish (`hindi`)	135	91.1%	80.7%	94.8%	99.3%
Arabic Arabizi (`arabic`)	138	88.4%	67.4%	84.1%	85.5%
Russian Translit (`russian`)	100	98.0%	52.0%	88.0%	91.0%
Greek Greeklish (`greek`)	100	85.0%	49.0%	77.0%	85.0%
Vietnamese Telex / ASCII (`vietnamese`)	100	97.0%	43.0%	84.0%	88.0%
Spanish ASCII (`spanish`)	100	96.0%	71.0%	85.0%	93.0%
French ASCII (`french`)	100	95.0%	77.0%	92.0%	87.0%
Portuguese ASCII (`portuguese`)	100	99.0%	88.0%	97.0%	99.0%
German ASCII / Umlaut (`german`)	100	99.0%	88.0%	96.0%	100.0%
Italian ASCII (`italian`)	100	99.0%	83.0%	91.0%	94.0%

Version History & Reproducible Revisions

This repository tracks the latest 2.x release on main while preserving immutable Git tags for every milestone:

v2.6 (default / main): Initial public release of the 9B flagship offline tier (dataset_v5.1), supporting 12 languages / 13 output modes with 92.09% accuracy on the 708-case v4-aligned suite and 90.94% on Core-5 (773 cases).
```
huggingface-cli download UnimeType/Transliteration-2.0-9B-GGUF --revision v2.6
```

Downloads last month: 7

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

Model tree for UnimeType/Transliteration-2.0-9B-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(722)

this model

UnimeType
/

Transliteration-2.0-9B-GGUF

UnimeType Transliteration 2.0 9B — v2.6 (12-Language Offline IME Engine · GGUF Q4_K_M & Q8_0)

Official `v2.6` Model Family (`0.8B` · `4B` · `9B`)

Included GGUF Quantizations

What's New in `v2.6`

Quickstart: `unimetype-convert-short-v3` Compact JSON Protocol

Evaluation Benchmarks (`v2.6`)

1. Six-Suite Head-to-Head Benchmark: Offline `v2.6` (`0.8B / 4B / 9B`) vs. Cloud `DeepSeek V4.1 Flash`

2. Per-Language Strict Accuracy Across All 12 Languages / 13 Modes (`1,573` Held-Out Cases)

Version History & Reproducible Revisions

Model tree for UnimeType/Transliteration-2.0-9B-GGUF

Space using UnimeType/Transliteration-2.0-9B-GGUF 1

UnimeType Transliteration 2.0 9B — v2.6 (12-Language Offline IME Engine · GGUF Q4_K_M & Q8_0)

Official v2.6 Model Family (0.8B · 4B · 9B)

Included GGUF Quantizations

What's New in v2.6

Quickstart: unimetype-convert-short-v3 Compact JSON Protocol

Evaluation Benchmarks (v2.6)

1. Six-Suite Head-to-Head Benchmark: Offline v2.6 (0.8B / 4B / 9B) vs. Cloud DeepSeek V4.1 Flash

2. Per-Language Strict Accuracy Across All 12 Languages / 13 Modes (1,573 Held-Out Cases)

Version History & Reproducible Revisions

Model tree for UnimeType/Transliteration-2.0-9B-GGUF

Space using UnimeType/Transliteration-2.0-9B-GGUF 1

Official `v2.6` Model Family (`0.8B` · `4B` · `9B`)

What's New in `v2.6`

Quickstart: `unimetype-convert-short-v3` Compact JSON Protocol

Evaluation Benchmarks (`v2.6`)

1. Six-Suite Head-to-Head Benchmark: Offline `v2.6` (`0.8B / 4B / 9B`) vs. Cloud `DeepSeek V4.1 Flash`

2. Per-Language Strict Accuracy Across All 12 Languages / 13 Modes (`1,573` Held-Out Cases)