FitMyLLM
Google/Dense

GoogleGemma 3 270M

Gemma 3 270M from Google: dense, 270M parameters, 32K context.

chat
0.27B
Parameters
32K
Context length
11
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2025-08-14
Layers
18
KV Heads
4
Head Dim
256
Family
gemma

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
1.5 GB
0.7 + 0.8 KV
good
Q5_K_S5.57
1.5 GB
0.7 + 0.8 KV
good
Q5_K_M5.7
1.5 GB
0.7 + 0.8 KV
good
Q6_K6.56
1.6 GB
0.7 + 0.8 KV
excellent
Q8_08.5
1.6 GB
0.8 + 0.8 KV
lossless
FP1616
1.9 GB
1.0 + 0.8 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 Gemma 3 270M now

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

Community Ratings

Loading ratings...

Benchmarks (11)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# Gemma 3 270M is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=gemma-3-270m-it+GGUF), or use the vLLM tab with the original weights.

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.

Find the best GPU for Gemma 3 270M

Build Hardware for Gemma 3 270M
Spec sheet

Gemma 3 270M — 0.27B Dense.

Specifications
Parameters
0.27B
Architecture
Dense Transformer
Context Length
32K tokens
Capabilities
chat
Release Date
2025-08-14
Provider
Google
Family
gemma
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.890.7 GB94%
Q5_K_S5.570.7 GB96%
Q5_K_M5.70.7 GB96%
Q6_K6.560.7 GB97%
Q8_08.50.8 GB100%
FP16161.0 GB100%
Benchmark scores
IFEval51.2
BBH26.7
GPQA Diamond22.4
LiveCodeBench0.3
AIME2.3
HLE4.2
AA Intelligence7.7
AA Coding0.0
AA Math2.3
IFBench12.1
τ²-Bench9.1
Compatible GPUs
30 @ Q4_K_M