SmolLM · Ollama

smollm2

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

tools 135m 360m 1.7b

4M Pulls 49 Tags Updated 1 year ago

solar-pro

Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU

22b

563.8K Pulls 18 Tags Updated 2 years ago

granite4.1-guardian

Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.

tools thinking 8b

26.6K Pulls 16 Tags Updated 3 months ago

llama-guard3

Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.

1b 8b

1M Pulls 33 Tags Updated 1 year ago

qwen2-math

Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).

1.5b 7b 72b

1.1M Pulls 52 Tags Updated 2 years ago

minicpm-v

A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

vision 8b

5.5M Pulls 17 Tags Updated 1 year ago

Yarflam/SmolLM3-Q4KM

Thinking model - efficient

49 Pulls 1 Tag Updated 2 months ago

Impulse2000/smollm3

SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports dual mode reasoning, 6 languages and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.

thinking

1,314 Pulls 5 Tags Updated 10 months ago

ahmadwaqar/smolvlm2-2.2b-instruct

SmolVLM2-2.2B-Instruct is a compact multimodal model for image and video understanding. Built on SmolLM2-1.7B with SigLIP vision encoder. Supports visual QA, OCR, and video analysis. Available in Q8 and FP16 quantizations. Apache 2.0 license.

vision

1,143 Pulls 2 Tags Updated 9 months ago

cambered/100M

Thanks to hugging face for SmolLM 360m while 100m is WIP.

12 Pulls 1 Tag Updated 1 month ago

schroneko/smollm-135m

SmolLM-135M-GGUF quantized to Q4_0 GGUF for efficient inference.

82 Pulls 1 Tag Updated 6 months ago

alibayram/smollm3

SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages, advanced reasoning and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.

87.9K Pulls 1 Tag Updated 1 year ago

CygnisAI/Cygnis-Alpha-1.7B-v0.1

Cygnis Alpha 1.7B v0.1 is a compact, high-efficiency LLM powered by SmolLM2. Fine-tuned by Simonc-44, it features a unique sovereign reasoning identity and superior accuracy for French linguistic nuances.

54 Pulls 1 Tag Updated 6 months ago

tarek-abdelhak/tarek-abdelhak-model

tarek-abdelhak-model is a fine-tuned version of SmolLM2-1.7B-Instruct trained to answer questions about Tarek Abdelhak, a Mid-Senior Frontend Engineer with 4 years of professional experience.

1 Pull 1 Tag Updated 2 weeks ago

wesjos/SmolLM3-Fu

This model is trained to be impolite when speaking in Chinese or sometime English

3b

22 Pulls 1 Tag Updated 10 months ago

jace-ai/SmolLM2-German-Instruct

Extensively pre-trained and instruction fine-tuned version of SmolLM2 360M, now supercharged with German language capabilities!

360m

551 Pulls 4 Tags Updated 1 year ago

thirdeyeai/SmolLM2-1.7B-Instruct-Uncensored.gguf

591 Pulls 3 Tags Updated 1 year ago

saicharan1010/SmolLM2-FT-legal-india

This is a fine-tuned version of the SmolLM2-135M-Instruct model, trained on legal texts from the Indian-Law dataset by vishnun0027 on Hugging Face.

103 Pulls 1 Tag Updated 1 year ago

unclemusclez/unsloth-smollm

SmolLM with Unsloth

135m 360m

107 Pulls 75 Tags Updated 1 year ago

unclemusclez/smollm-135m-instruct-devinator

SmolLM 135M Instruct Trained on DEVINator Data for Open Hands (Open Devin)

92 Pulls 51 Tags Updated 2 years ago