whatmodel.sh / TranslateGemma 12B

TranslateGemma 12B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

TranslateGemma 12B is an open-weights language model from Google, released January 2026. Its published size is 13.19B parameters. Licence: gemma.

Catalogue identity notes

google/translategemma-12b-it @d1b225e (created 2026-01-12, licence gemma). Google TranslateGemma 12B (Jan 2026), Gemma 3 12B fine-tuned for translation across 55 languages (text and image input; gated Gemma terms). Lab row from the CC BY technical report (Comet22 on WMT24++) next to the catalogued Gemma 3 12B baseline.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 13,194,203,760 parameters.

64.1±10.4#168 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of TranslateGemma 12B, out of 1132 with a score, then more from Google.

#modelscorewhereRAMreleased
208Nemotron-Labs-3 Puzzle 75B-A9B NVIDIA64±1local~35GB2026-06
209Qwen3-VL 235B-A22B Thinking Alibaba64±1local~111GB2025-09
210TranslateGemma 12B Google64±10local~8.4GB2026-01
211Qwen3-Coder 480B-A35B Instruct Alibaba64±1api $0.67/M +local~78GB2025-07
212Mistral Medium 3.1 (2508) Mistral64±2comparison only2025-08
more from Google
9Gemini 4 Argon (limited preview) Google82±1limited preview2026-09
23Gemini 3.8 Flash Google77±1api $1.50/M2026-09
32Gemini 3.7 Flash Google76±1api $1.50/M2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 52% of its score
testresultvs the others in its rundifficultycountswhy
WMT24++ lab83.5% ✎█···█·█··███ beats 4/5easy · avg 72%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 52%blunt

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run TranslateGemma 12B · needs ~7.3 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/translategemma-12b-it-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/translategemma-12b-it-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run TranslateGemma 12B · needs ~7.3 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/translategemma-12b-it-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run TranslateGemma 12B · needs ~8.1 GB · from ollama.com
    chat in the terminal
    ollama run translategemma:12b

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run TranslateGemma 12B · needs ~6.6 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/translategemma-12b-it-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/translategemma-12b-it-4bit

Official weights and documentation: huggingface.co/google ↗

$ how the score was worked out · TranslateGemma Technical Repo… 52%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
TranslateGemma Technical Report (Google), arXiv 2601.09012v2 · lab-reported1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 52%CC BY 4.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%
weighted average= 64.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json