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. | 1.8B/3.25B | 7B/13B/70B |
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. | 32k | 4k |
| Overview | ||
| Company | Meta | |
| Release date | Dec 6 2023 | Jul 18 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 1.0 NanovsClaude Haiku 5.5LLaMA 2vsClaude Haiku 5.5Gemini 1.0 NanovsGPT-6.1 SolLLaMA 2vsGPT-6.1 SolGemini 1.0 NanovsGrok 4.7LLaMA 2vsGrok 4.7Gemini 1.0 NanovsDeepSeek-V4.1-Flash-1017LLaMA 2vsDeepSeek-V4.1-Flash-1017Gemini 1.0 NanovsMistral Large 4LLaMA 2vsMistral Large 4Gemini 1.0 NanovsKimi K3LLaMA 2vsKimi K3Frequently asked questions
Gemini 1.0 Nano and LLaMA 2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 2 shipped 141 days before Gemini 1.0 Nano, so benchmark comparisons should account for the intervening progress.
Gemini 1.0 Nano has 1.8B/3.25B parameters, while LLaMA 2 has 7B/13B/70B. Context windows are 32k (Gemini 1.0 Nano) vs 4k (LLaMA 2). Gemini 1.0 Nano is closed, while LLaMA 2 is open weight.
Direct benchmark comparisons are unavailable — Gemini 1.0 Nano and LLaMA 2 don't publish scores on any of the same benchmarks.