Heavy tier

Gemma 3 27B

Google · Gemma

The largest Gemma 3 model and one of the best open-weight models in the 20–30B range. Fits in a single RTX 4090 (24 GB) with room to spare at Q4 quantization, and delivers instruction-following quality that rivals models twice its size.

Params

27B

License

Gemma Terms of Use

Context

128K

Min VRAM

15 GB

Min RAM

32 GB

Tier

Heavy

Run locally with Ollama

terminal
ollama run gemma3:27b

Once running, Ollama exposes an OpenAI-compatible endpoint at localhost:11434/v1.

Will it run on my hardware?

Gemma 3 27B needs about 15 GB of fast memory at Q4. Here is what in our hardware database clears that bar.

Runs at full speed · 11

NVIDIA RTX 5090 32GB32 GB VRAM~$2,999Amazon
NVIDIA RTX 5080 16GB16 GB VRAM~$1,250Amazon
NVIDIA RTX 5070 Ti 16GB16 GB VRAM~$999Amazon
NVIDIA RTX 4060 Ti 16GB16 GB VRAM~$424Amazon
NVIDIA RTX 4080 Super 16GB16 GB VRAM~$1,000Amazon
NVIDIA RTX 4090 24GB24 GB VRAM~$2,755Amazon
AMD RX 7900 XTX 24GB24 GB VRAM~$1,339Amazon
Apple Mac mini M4 (16 GB)16 GB unified$799Amazon
Apple Mac mini M4 Pro (24 GB)24 GB unified$1,599Amazon
Apple Mac mini M4 Pro (48 GB)48 GB unified$2,099Amazon
Apple Mac Studio M4 Max (64 GB)64 GB unified$2,899Amazon

Runs, but slower on shared memory · 3

MINISFORUM AI X1 Pro32 GB DDR5 (shared)~$699Amazon
Corsair Vengeance 64 GB DDR5 Kit64 GB DDR5~$1,150Amazon
G.Skill Trident Z5 128 GB DDR5128 GB DDR5~$2,200Amazon

1 other tracked configuration do not have enough memory.

Hardware links are affiliate links. We earn a small commission if you buy through them — at no extra cost to you. Disclosure

Specifications

Parameters27B
Context window128K
LicenseGemma Terms of Use
Min VRAM (Q4)15 GB
Min RAM32 GB
Recommended tierHeavy
Best forcodinganalysischatcreative writing

Variants on Ollama

Ollama serves the Q4_K_M quantization by default. Higher-precision tags exist for users with more memory.

Gemma 3 27B

default · Q4_K_M
ollama run gemma3:27b
higher precision · q8_0 (generic tag)
ollama pull gemma3:q8_0
full precision · fp16 (generic tag)
ollama pull gemma3:fp16

Exact quantization tags vary per model — run ollama show gemma3 or check the tags page for the full list.

Popularity trend (illustrative)

Illustrative adoption trend, not actual download counts. We do not publish a download number for any model because we have no honest source for it.

Similar models