Gemma 2 27B.
Gemma 2 27B is Google's open-weights English text model under the Gemma license, instruction-tuned here, for chat, summarization and question answering.
1× NVIDIA Quadro RTX 6000 · $0.14/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Variants in the Gemma family.
Google's open-weight multimodal LLM — efficient and license-permissive.
9B Gemma 2 — single-GPU local target.
Tiny 2B Gemma 2 — laptop / mobile.
Gemma 3 4B is Google's small open-weights model with text and image input and...
1B Gemma 3 — edge / mobile.
Gemma 3 introduces multimodality, supporting vision-language input and text o...
Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resour...
Gemma 4 26B A4B is Google DeepMind's Apache 2.0 mixture-of-experts model, 25....
Google DeepMind's instruction-tuned 31B dense open-weights model for coding, ...
Frequently asked.
How do I run Gemma 2 27B?
Where can I access Gemma 2 27B?
How much does it cost to run Gemma 2 27B?
Is Gemma 2 27B open-source or proprietary?
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr is the cheapest rate on offer now. A multi-card setup uses a real instance of that size when one is rented; otherwise it is the single-card rate times the count.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
96 GB |
$0.52/hr
est. 2 × single-card rate
Vast.ai · on-demand
|
— | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
48 GB |
$0.26/hr
Vast.ai · on-demand
|
17.3 | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
24 GB |
$0.14/hr
Vast.ai · on-demand
|
34.6 | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Gemma 2 27B across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like Gemma 2 27B, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month. Power is included in a rental's hourly price.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About Gemma 2 27B.
Gemma 2 27B is an open-weights text model from Google, built from the research behind Gemini, and published here in its instruction-tuned form. It is a decoder-only model that takes a text string and generates English text. Google lists question answering, summarization, chatbots, code and language learning among its uses, and says the family's small size suits limited hardware. Access requires accepting the Gemma license. Google warns it can state incorrect or outdated facts and handles open-ended tasks less well.