LLM Reference

Gemma 7B Instruct

Released
2024-02-21
Last refreshed
2026-05-11
Status
Researched 54d ago
Open WeightsCommercial use with conditionsCodingClassificationJSON / Tool use

Gemma 7B Instruct is worth evaluating for coding, classification, and json / tool use when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, classification, and json / tool use
  • Workloads that can use a 8k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Gemma
Released
2024-02-21
Context
8k
Parameters
7B
Architecture
Decoder Only
Knowledge cutoff
2023-04
Specialization
general
Openness
Open weights
License
GemmaCommercial use with conditions
Training
finetuned
Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
$0.070
Input / 1M
$0.070

Cheapest of 8 routes · Lepton AI API

About

Gemma 7B Instruct is a cutting-edge large language model developed by Google DeepMind, boasting 7 billion parameters. As part of the Gemma family, it benefits from the advanced research underpinning Google's Gemini models. This model is optimized for text generation tasks, excelling in areas like question answering and summarization, and it is finely tuned to follow instructions effectively. Despite its compact size, Gemma 7B Instruct performs impressively on benchmarks, making it versatile for deployment across various hardware platforms, from laptops to cloud infrastructure. Moreover, it is open-source, with accessible weights and incorporates responsible AI practices, such as data filtering and human feedback, to ensure safe and ethical use.

Gemma 7B Instruct is an open-weight model in the Gemma family. The structured metadata tracks a 8k-token context window and structured outputs. This page tracks provider routes through NVIDIA NIM, Fireworks AI, Together AI, and 5 more, with the cheapest tracked route listed at $0.05 input and $0.25 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 50.8, HellaSwag 89.2, and HumanEval 70.1.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ A

1 relevant benchmark in the decision map.

Classification

Q/$ A

2 relevant benchmarks in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 8

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Lepton AI API$0.070$0.070
Serverless
Fireworks AI$0.200$0.200
Provisioned
Together AI$0.200$0.200
Serverless
Replicate API$0.050$0.250
Serverless

Available via routers & gateways(14)

Capabilities

Structured Outputs

Benchmark peer barsfor Coding

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Google-Proof Q&A50.8diamondresearch
HellaSwag89.210-shothttps://arxiv.org/abs/2403.08295
HumanEval70.1pass@1https://arxiv.org/abs/2403.08295
Massive Multitask Language Understanding75.35-shothttps://arxiv.org/abs/2403.08295
Instruction-Following Evaluation42.6v2https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard

Migration checks

No linked migration route is available for this model yet.

Show all 32 popular comparisonssorted by 7-day search impressions