SmolLM2-135M
Hugging FaceLMArena
Not ranked on LMArena
LMArena only ranks the models it serves.
Discussion
2 posts this week
- Build a DevOps AI Assistant from Scratch🤖| SmolLM2 Fine-Tuning, Training & Optimization| Full SeriesFDX Academy · Oct 24, 20265 likes
- 🔥 Let's Fine-Tune SmolLM2!FDX Academy · Oct 17, 20262 likes
- 🚀 Building a DevOps AI Assistant with SmolLM2FDX Academy · Oct 11, 20262 likes
- The authors move from Gaussian mixtures to SmolLM2AutMn Lab - Bineet Ghosh · Oct 3, 20262 likes
- SmolLM2 and SmolLM3 - Benchmark and agentic codingCiprian Turcu · Oct 27, 20261 like
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioprithivMLmods/SmolLM2-135M-GGUF32 builds
- MLX · Apple silicon: mlx-lm, LM StudioSirSahOl/SmolLM2-135M-chat-mlx-4bit2 builds
- AWQ · vLLM, SGLangfbaldassarri/HuggingFaceTB_SmolLM2-135M-auto_awq-int4-gs64-sym2 builds
- GPTQ · vLLM, SGLanglilmeaty/SmolLM2-135M-Instruct-GPTQ18 builds
Most downloaded
- SmolLM2-135M-InstructHuggingFaceTB · Quantization783.1K downloads
- SmolLM2-135M-Instruct-GPTQlilmeaty · Quantization8.9K downloads
- SmolLM2-135M-GGUFprithivMLmods · Quantization7.6K downloads
- KrynexAI-1.4-150M-Mobile-ModelKrynexLabs · Quantization6.3K downloads
- llama-michuggingface-mic · Fine-tune3.4K downloads
BenchClub runs
Not runnable yet
Runs open once a SmolLM2-135M build is registered.
Other ≤3B models
See more
MiniCPM5-2BOpenBMB986.8K2.5B
LFM3-1.7BLiquid AI110K1.7B
Spark-X2.6-1.7BXHToken5.7K1.7B
MNN-Pocket-0.3Btaobao-mnn5.4K362M