Gemma 2 27B
Google · released Jun 24, 2024 · google/gemma-2-27b-it
- Type
- Open weightsGemma Terms of Use
- Params
- 27.2B
- Context
- 8K
about 6K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Gemma 2 is a 27.2-billion-parameter text model from Google released in 2024, available as downloadable weights under restricted terms. Its benchmark results are unusually scattered, with duplicate entries showing spreads of over four times on the same tests, and its context limit is tight for a model of this size.
Consider this if you want low input cost from the source provider and can work within an eight-thousand-token request limit, or if you need predictable throughput and NextBit's eight-tokens-per-second rate suits your workflow. Skip it if you need a permissive licence for commercial redistribution, a larger context window, or reliable benchmark scores to guide your choice.
The case for it
- Lowest input price among tracked offers from the source provider.
- Arena coding score of 1304.6 is the highest of its own benchmark suite, ahead of maths, instruction following, hard prompts, overall text and creative writing.
- Predictable throughput of eight tokens per second available from one host.
The case against it
- Severely limited context window for its parameter class: 8,192 tokens with no larger variant listed.
- Benchmark data is extremely inconsistent, with duplicate entries showing spreads of 4.2× on GPQA Diamond, 3.5× on MMLU-Pro and 3.3× on IFEval — suggesting unreliable evaluation or data quality issues.
- Restrictive Gemma Terms of Use limit commercial flexibility; not a permissive open-source licence.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)129th of 143 · 1289.2
CodingWriting and fixing code on its own
Arena Coding133rd of 143 · 1304.6
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Gemma 2 27B for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Gemma 2 27B placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 3.7 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 11.7 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 4.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.65 in / $0.65 out
- Context served
- 8K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.65 / $0.65 | 8K | not measured | Unknown | Unknown | Unknown |
| NextBitint4 | $0.65 / $0.65 | 8K | 55 tok/s | No | No | Confirmed |
| Google AI | $0.35 / $1.05 | not reported8K out | not measured | Unknown | Unknown | Unknown |
Across the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| NextBitint4 | ✗ | ✓ | ✓ |
| Google AI |
Tool calling: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. JSON output: 2 of 3 listings say yes, 1 publishes no parameter list. Strict schema: 2 of 3 listings say yes, 1 publishes no parameter list.
Models people weigh against Gemma 2 27B
When we formed this view
Dates behind this page
Prices last checked 6h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 1 of 3 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsGemma Terms of Use, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Gemma Terms of Use
Commercial use allowed, but Google's prohibited-use policy applies and can be updated over time — terms are less static than Apache/MIT.
Identifiers
- Hugging Face
- google/gemma-2-27b-it
- Modality record
- text->text
- Catalogue slug
- google-gemma-2-27b