Llama-3.2-3B
Meta LlamaLMArena
Not ranked on LMArena
LMArena only ranks the models it serves.
| Model | Params | Score |
|---|---|---|
| 1.2B | — | |
| 1.2B | 1055 | |
| 3.2B | — | |
| 3.2B | 1110 |
Discussion
- Como Instalar IA en Android (Ollama y LLama 3.2) - Sin RootBenhack · Oct 2, 202616 likes
- Building Real World Agentic AI Applications using Ollama, Langchain, Llama3.2 and ChromaDBcodestellar · Sep 13, 202610 likes
- Build Your Own Local AI Assistant with Ollama & Llama 3.2Design & Code Studio · Oct 26, 20268 likes
- Llama 3.2 Desbloqueado: Como Remover Todas as Restrições da IAGuilherme Nabor · Sep 9, 20266 likes
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioABDALLALSWAITI/llm_3_2_flux_prompt95 builds
- MLX · Apple silicon: mlx-lm, LM StudioQuantLLM/Llama-3.2-3B-8bit-mlx8 builds
- AWQ · vLLM, SGLangfbaldassarri/meta-llama_Llama-3.2-3B-auto_awq-int4-gs128-sym4 builds
- GPTQ · vLLM, SGLangfbaldassarri/meta-llama_Llama-3.2-3B-auto_gptq-int8-gs128-sym15 builds
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a Llama-3.2-3B build is registered.
More from Meta Llama
See more
Llama-3.1-8B-Instruct4.2M8.0B

Llama-3.2-1B-Instruct1.3M1.2B

Llama-3.2-3B-Instruct831.4K3.2B

Llama-3.2-1B644.1K1.2B
Other 3–9B models
See more
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA1.9M4.0B
granite-4.1-8bIBM Granite79.4K8.8B
Molmo2-8BAi247.6K8.7B
Spark-X2.6-4BXHToken32.9K4.1B