All modelsGoogle
Gemma 2 27B fastruns locally
google/gemma-2-27b-it
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
Input / 1M
$0.65
USD per million tokens
Output / 1M
$0.65
USD per million tokens
Est. cost / token
$0.00000065
$0.65 per 1M, 3:1 mix
Context window
8K
max output 2K
Major features
Open weightsJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context1
- agentic1
Run it locally
Will it run on my machine? →ollama run gemma2:27b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 14.4 GB |
| Q3_K_M | fair | 16.4 GB |
| Q4_K_Mrecommended | good | 19.9 GB |
| Q5_K_M | very good | 22.7 GB |
| Q6_K | excellent | 25.8 GB |
| Q8_0 | near-lossless | 32.7 GB |
| F16 | lossless | 59.5 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.65 | $0.65 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.65
- Output
- $0.65
- Blended (3:1)
- $0.65
Details
- Company
- Version
- 2
- Family
- Gemma
- Released
- 2024-07-13
- Parameters
- 27.2B
- Max output
- 2K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 29 min ago