Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 2B/7B | 7B/13B/34B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 8k | 16k |
| Overview | ||
| Company | Meta | |
| Release date | Feb 21 2024 | Aug 24 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemma 1vsClaude Haiku 5.5Code LlamavsClaude Haiku 5.5Gemma 1vsGPT-6.1 SolCode LlamavsGPT-6.1 SolGemma 1vsGrok 4.7Code LlamavsGrok 4.7Gemma 1vsDeepSeek-V4.1-Flash-1017Code LlamavsDeepSeek-V4.1-Flash-1017Gemma 1vsMistral Large 4Code LlamavsMistral Large 4Gemma 1vsKimi K3Code LlamavsKimi K3Frequently asked questions
Gemma 1 and Code Llama don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama shipped 181 days before Gemma 1, so benchmark comparisons should account for the intervening progress.
Gemma 1 has 2B/7B parameters, while Code Llama has 7B/13B/34B. Context windows are 8k (Gemma 1) vs 16k (Code Llama).
Direct benchmark comparisons are unavailable — Gemma 1 and Code Llama don't publish scores on any of the same benchmarks.