FitMyLLM
Google/Dense

Googlegemma-3-27b

chatThinking
27.4B
Parameters
4K
Context length
21
Benchmarks
10
Quantizations
1.2M
HF downloads
Architecture
Dense
Released
2025-03-12
Layers
62
KV Heads
16
Head Dim
128
Family
gemma

Quantization Options

QuantBitsVRAMQuality
Q3_K_M414.2 GBlow
Q3_K_L4.315.2 GBmoderate
IQ4_XS4.4615.8 GBmoderate
Q4_K_S4.6716.5 GBmoderate
Q4_K_M4.8917.2 GBgood
Q5_K_S5.5719.6 GBgood
Q5_K_M5.720.0 GBgood
Q6_K6.5623.0 GBexcellent
Q8_08.529.6 GBlossless
FP161655.3 GBlossless

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

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GEMMA-3-27B NOW

Rent on RunPod →Or Vast.ai →

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

Community Ratings

Loading ratings...

Benchmarks (21)

Arena Elo1359
MATH-50088.3
IFEval79.8
BBH49.3
BigCodeBench42.8
GPQA Diamond42.8
MMLU-PRO38.3
IFBench31.8
MATH23.9
SciCode21.2
AIME20.7
AA Math20.7
GPQA16.7
LiveCodeBench13.7
τ²-Bench10.5
AA Intelligence10.3
AA Coding9.6
MUSR9.1
AA Long Context5.7
HLE4.7
Terminal-Bench3.8

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run gemma3:27.4b-instruct-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
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M3 Pro (18GB)
18 GB VRAM • 150 GB/s
APPLE
$1599
AMD RX 7900 XT
20 GB VRAM • 800 GB/s
AMD
$849
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4000 Ada 20GB
20 GB VRAM • 432 GB/s
NVIDIA
$1250
AmazonNeweggeBayPCPartPicker
NVIDIA A10M
20 GB VRAM • 500 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 3080 Ti 20 GB
20 GB VRAM • 760 GB/s
NVIDIA
$1199
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 7900 XT
20 GB VRAM • 800 GB/s
AMD
$899
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4000 Ada Generation
20 GB VRAM • 360 GB/s
NVIDIA
$1250
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4000 SFF Ada Generation
20 GB VRAM • 280 GB/s
NVIDIA
$1250
AmazonNeweggeBayPCPartPicker
NVIDIA RTX A4500
20 GB VRAM • 640 GB/s
NVIDIA
$2000
NVIDIA RTX 4090
24 GB VRAM • 1008 GB/s
NVIDIA
$1599
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3090 Ti
24 GB VRAM • 1008 GB/s
NVIDIA
$999
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3090
24 GB VRAM • 936 GB/s
NVIDIA
$850
AmazonNeweggeBayPCPartPicker
AMD RX 7900 XTX
24 GB VRAM • 960 GB/s
AMD
$999
AmazonNeweggeBayPCPartPicker
Apple M4 Pro (24GB)
24 GB VRAM • 273 GB/s
APPLE
$1399
NVIDIA L4 24GB
24 GB VRAM • 300 GB/s
NVIDIA
$2500
NVIDIA A10 24GB
24 GB VRAM • 600 GB/s
NVIDIA
$3500
AmazonNeweggeBayPCPartPicker
Apple M2 (24GB)
24 GB VRAM • 100 GB/s
APPLE
$999
Apple M3 (24GB)
24 GB VRAM • 100 GB/s
APPLE
$999
Apple M4 (24GB)
24 GB VRAM • 120 GB/s
APPLE
$699
NVIDIA Tesla M40 24 GB
24 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla P10
24 GB VRAM • 694 GB/s
NVIDIA
NVIDIA Tesla P40
24 GB VRAM • 347 GB/s
NVIDIA
NVIDIA Quadro RTX 6000
24 GB VRAM • 672 GB/s
NVIDIA
$4000
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro RTX 6000 Passive
24 GB VRAM • 624 GB/s
NVIDIA
$4000
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 3090
24 GB VRAM • 936 GB/s
NVIDIA
$1499
AmazonNeweggeBayPCPartPicker
NVIDIA A10 PCIe
24 GB VRAM • 600 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA A10G
24 GB VRAM • 600 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA RTX A5000
24 GB VRAM • 768 GB/s
NVIDIA
$2500
NVIDIA GeForce RTX 3090 Ti
24 GB VRAM • 1010 GB/s
NVIDIA
$1999
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 4090
24 GB VRAM • 1010 GB/s
NVIDIA
$1599
AmazonNeweggeBayPCPartPicker

Find the best GPU for gemma-3-27b

Build Hardware for gemma-3-27b

Model Card

View on HuggingFace

Read the full model card for detailed information about this model.

▸ SPEC SHEET

gemma-3-27b — 27.4B Dense.

▸ SPECIFICATIONS
PARAMETERS
27.4B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
4K tokens
CAPABILITIES
chat
RELEASE DATE
2025-03-12
PROVIDER
Google
FAMILY
gemma
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q3_K_M414.2 GB88%
Q3_K_L4.315.2 GB90%
IQ4_XS4.4615.8 GB92%
Q4_K_S4.6716.5 GB93%
Q4_K_M4.8917.2 GB94%
Q5_K_S5.5719.6 GB96%
Q5_K_M5.720.0 GB96%
Q6_K6.5623.0 GB97%
Q8_08.529.6 GB100%
FP161655.3 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO38.3
MATH23.9
IFEval79.8
BBH49.3
GPQA16.7
MUSR9.1
BigCodeBench42.8
Arena Elo1359.0
GPQA Diamond42.8
LiveCodeBench13.7
AIME20.7
MATH-50088.3
HLE4.7
AA Intelligence10.3
AA Coding9.6
AA Math20.7
aa_ifbench31.8
aa_terminal_bench3.8
aa_tau210.5
aa_scicode21.2
aa_lcr5.7
§ 02RUN COMMAND

Run gemma-3-27b locally with Ollama — needs 17.2 GB VRAM at Q4_K_M:

$ollama run gemma3:27.4b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
Apple M3 Pro (18GB)
18 GB · 150 GB/s
AMD RX 7900 XT
20 GB · 800 GB/s
NVIDIA RTX 4000 Ada 20GB
20 GB · 432 GB/s
NVIDIA A10M
20 GB · 500 GB/s
NVIDIA GeForce RTX 3080 Ti 20 GB
20 GB · 760 GB/s
AMD Radeon RX 7900 XT
20 GB · 800 GB/s
NVIDIA RTX 4000 Ada Generation
20 GB · 360 GB/s
NVIDIA RTX 4000 SFF Ada Generation
20 GB · 280 GB/s
NVIDIA RTX A4500
20 GB · 640 GB/s
NVIDIA RTX 4090
24 GB · 1008 GB/s
NVIDIA RTX 3090 Ti
24 GB · 1008 GB/s
NVIDIA RTX 3090
24 GB · 936 GB/s
AMD RX 7900 XTX
24 GB · 960 GB/s
Apple M4 Pro (24GB)
24 GB · 273 GB/s
NVIDIA L4 24GB
24 GB · 300 GB/s