Gemma 3 27B
GoogleReleased Mar 12, 2025Open weights · Gemma Terms of Usegemma-3-27b
- Intelligence (Epoch)
- 130 · 96th of 111
- Reasoning
- no
- Knowledge cutoff
- January 2025
- Context
- 128k tokens
- Max output
- 16k tokens
- Input
- text, image
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Google · cutoff: ai.google.dev
Intelligence for the price
6 models score higher for the same price or less; it ranks 7 of the 12 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 130 with an interval of 124 to 132.
Against its rivals
Its previous version, the best of its price range and the top score
- Gemma 3 27Bthis model$0.24130
- Claude Opus 5.5top score$24.00169
- DeepSeek V4.1 Flashsame price range$0.47156
- DeepSeek V4 Flash 0731same price range$0.21155
- Gemma 2 27Bprevious version$1.30122
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Speed by provider
Output speed of Gemma 3 27B at each host, fastest first
- Nebius39 tok/s1.32 s to first token
- Parasail32 tok/s0.75 s to first token
- NextBit19 tok/s0.69 s to first token
- DeepInfra17 tok/s2.25 s to first token
Speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · a snapshot of real traffic before the daily read, not a daily average · bars from zero.
Run it yourself
open weights, Gemma Terms of Use · fits 6 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 27B
- dense
- Memory needed
- 16 GB
- in INT4 · 32 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 517M tokens
- a month, against the cheapest API at $0.24 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 16 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 32 GB | A100 · $1.19/h | near-lossless |
| FP16 (full) | 65 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 15B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| NextBitfp8 · 128K ctx | $0.08 | $0.35 | $0.04 | 19 | 0.69 s | 99.2% | Oct 23 |
| Parasailfp8 · 128K ctx | $0.08 | $0.45 | $0.04 | 32 | 0.75 s | 94.2% | Oct 23 |
| DeepInfrafp8 · 128K ctx · 16K out | $0.08 | $0.16 | — | 17 | 2.25 s | 99.9% | Oct 23 |
| Novita AIbf16 · 96K ctx (128K) · 16K out | $0.12 | $0.20 | — | — | — | — | Oct 23 |
| Nebiusfp8 · 110K ctx (128K) | $0.10 | $0.30 | — | 39 | 1.32 s | 95.3% | Oct 23 |
5 of 5 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 128K | 16K | yes | yes | no |
| Novita AI | bf16 | 96K | 16K | no | no | no |
| Nebius | fp8 | 110K | not stated by the host | no | yes | no |
| NextBit | fp8 | 128K | not read: host terms | no | yes | no |
| Parasail | fp8 | 128K | not read: host terms | no | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Gemma 3 27B spec sheet, field by field, with sources
Gemma 3 27B spec sheetmaker-declared
What Google declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- weights repository under access conditions
- Parameters
- weights repository under access conditions
- Active experts
- weights repository under access conditions
- Weight precision
- weights repository under access conditions
- License
- Gemma Terms of Use — open weights, conditionalcuratedScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- January 2025maker's docs
- Modalities
- weights repository under access conditions
- Max output (official)
- to verify
- Release date
- to verify≈ March 12, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
google/gemma-3-27b-it · weights repository @ 005ad34 · file not readable · read 2026-10-08 · 2 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 15 | NextBit | $0.07 → $0.08 | $0.28 → $0.35 | +25% |
| Oct 14 | NextBit | $0.08 → $0.07 | $0.30 → $0.28 | −9% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.16 | $0.72 | $0.48 |
| Novita AI | $0.22 | $1.05 | $0.68 |
| Nebius | $0.25 | $0.95 | $0.70 |
| NextBit | $0.26 | $0.81 | $0.67 |
| Parasail | $0.30 | $0.86 | $0.77 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Google models · all its models, hosts and history ›
- Gemma 4 31B14 providers · from $0.38
- Gemma 4 26B A4B12 providers · from $0.26
- Gemma 3 12B3 providers · from $0.15
- Gemma 3 4B2 providers · from $0.09
- Gemini 2.5 Flash1 provider · from $2.80
- Gemini 2.5 Pro1 provider · from $11.25