FitMyLLM
Google/Dense

GoogleTranslateGemma 4B

TranslateGemma 4B — Google's translation model for 7 languages.

chatmultilingualvision
4.97B
Parameters
128K
Context length
6
Benchmarks
6
Quantizations
109K
HF downloads
Architecture
Dense
Released
2026-01-13
Layers
34
KV Heads
4
Head Dim
256
Family
gemma

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.1 GB
3.5 + 1.6 KV
good
Q5_K_S5.57
5.5 GB
3.9 + 1.6 KV
good
Q5_K_M5.7
5.6 GB
4.0 + 1.6 KV
good
Q6_K6.56
6.2 GB
4.6 + 1.6 KV
excellent
Q8_08.5
7.4 GB
5.8 + 1.6 KV
lossless
FP1616
12.0 GB
10.4 + 1.6 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN TRANSLATEGEMMA 4B NOW

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (6)

IFEval19.7
MMLU-PRO3.5
BBH3.5
MATH2.3
MUSR2.1
GPQA1.7

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run translategemma:4b-it-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C1080
4 GB VRAM • 102 GB/s
NVIDIA
NVIDIA Tesla K10
4 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M4
4 GB VRAM • 88 GB/s
NVIDIA
AMD Radeon Instinct MI8
4 GB VRAM • 512 GB/s
AMD
NVIDIA RTX A1000 Embedded
4 GB VRAM • 224 GB/s
NVIDIA
NVIDIA RTX A2000 Embedded
4 GB VRAM • 192 GB/s
NVIDIA

Find the best GPU for TranslateGemma 4B

Build Hardware for TranslateGemma 4B

TranslateGemma 4B — Google's translation model for 7 languages.

▸ SPEC SHEET

TranslateGemma 4B4.97B Dense.

▸ SPECIFICATIONS
PARAMETERS
4.97B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
chat, multilingual, vision
RELEASE DATE
2026-01-13
PROVIDER
Google
FAMILY
gemma
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.893.5 GB94%
Q5_K_S5.573.9 GB96%
Q5_K_M5.74.0 GB96%
Q6_K6.564.6 GB97%
Q8_08.55.8 GB100%
FP161610.4 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO3.5
MATH2.3
IFEval19.7
BBH3.5
GPQA1.7
MUSR2.1
§ 02RUN COMMAND

Run TranslateGemma 4B locally with Ollama — needs 3.5 GB VRAM at Q4_K_M:

$ollama run translategemma:4b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M