Public preview · figures are illustrative fixture data, attributed to their source · data to May 2025 · read-only
Model · Gemma 2 · June 2024

Gemma 2 27B

A 27 billion-parameterHow many numbers the model learned during training — the usual rough measure of its size. dense model from Google DeepMind. 9B and 27B models with interleaved local/global attention.

Size
27.2Bdense
Memory to run
~20 GBsmallest, 8K ctx
Context
8Ktokens
License
RestrictedGemma Terms of Use
Updated

Which version to use

  • Variant Gemma 2 27B IT · Google DeepMind
    Tuned to follow instructions and hold a conversation. The usual choice.
    Chat

Other sizes in Gemma 2: Gemma 2 9B

Where it runs

Best-fitting version on each reference system, at an 8K contextHow much text the model can consider at once, counted in tokens — roughly ¾ of a word each..

Runs well 11

Slowly (CPU or offload) 2

Too large 0

None of the reference systems.

Benchmarks

Each benchmarkA fixed set of questions every model is given, so their scores can be compared on the same task. is developer-reported; prompts and settings differ between labs. Bars are relative to the best open result.

No benchmark results recorded for this model.

Variants & downloads

Each variant is a separate set of weights. Expand one for its downloads: quantizationStoring each of the model’s numbers with fewer bits, so the file is smaller and needs less memory. trades a little quality for a much smaller file, and the memory column adds the working memoryExtra space the model needs while it answers. It grows with the length of the conversation, on top of the file itself. a conversation needs on top.

Variant Gemma 2 27B ITinstruct · Google DeepMind · 2 downloads · Gemma Terms of UseRestricted
What it is
Tuned to follow instructions and hold a conversation. The usual choice.
Publisher
Google DeepMind
License
Gemma Terms of Use · commercial use restricted
Released
27 Jun 2024

Contributions are not open yet, so there is nothing here from members.

QuantizationFormatBitsDownloadMemory @ 8KPublisher
Download BF16nativesafetensors1650.7 GiB~56.1 GiBGoogle DeepMindgoogle/gemma-2-27b-it
Download Q4_K_Mk quantgguf4.8915.5 GiB~19.5 GiBLM Studio Communitylmstudio-community/gemma-2-27b-it-GGUF
Architecture detailsLayers, attention and KV cache geometry
Parameters
27.23B
Active / token
All (dense)
Architecture
Dense
Layers
46
Attention heads
32
KV heads
16
Head dim
128
KV cache @ 8K (fp16)
2.88 GiB
Max context
8,192 tokens

Measured performance

Throughput on specific systems and runtimes, with the source of each measurement.

No performance measurements recorded yet.

Community results

Contributions are not open yet, so there is nothing here from members.

Reviews

Contributions are not open yet, so there is nothing here from members.

Lineage

How this model’s variants relate to each other and to other models.

VariantGemma 2 27B IT instruct

Sources & history

Sources

No source records linked.

External identifiers