sam860

sam860

I upload models and quants that I like, or would like people to have easy downloads for.

qwen3

Useful Unsloth-DQ2 quants of the smaller qwen3 models

tools thinking 1.7b 4b 8b

1,682 Pulls 21 Tags Updated 1 month ago
deepseek-r1-0528-qwen3

Useful DQ2 quants for deepseek-r1-0528-qwen3-distill:8b

8b

1,285 Pulls 3 Tags Updated 6 months ago
dolphin3-qwen2.5

Dolphin 3.0 Qwen 2.5 🐬 - A powerful, customizable AI model for local use.

tools 1.5b 3b

1,019 Pulls 9 Tags Updated 9 months ago
LFM2

Small models made to run on mobile devices, developed by Liquid AI

350m 700m 1.2b 2.6b 8b

905 Pulls 17 Tags Updated 1 month ago
qwen3-reranker

tools

863 Pulls 2 Tags Updated 6 months ago
dolphin3-llama3.2

Dolphin 3.0 llama3.2 🐬 - A powerful, customizable AI model for local use.

1b 3b

857 Pulls 9 Tags Updated 6 months ago
qwen3-embedding

tools

806 Pulls 2 Tags Updated 6 months ago
granite-embedding-multilingual

Embedding models supporting multiple languages, made by the IBM-Granite team, in 2 (small) sizes

embedding

577 Pulls 4 Tags Updated 11 months ago
amoral-gemma3-1b-v2

gemma3 finetuned for neutral, non-judgemental responses

320 Pulls 6 Tags Updated 5 months ago
granite-4.0

Efficient, intelligent, and tiny models from IBM

tools 350m 1b 3.2b 3.4b 7b

300 Pulls 17 Tags Updated 1 month ago
phi4-mini

Phi-4-mini is the latest small LLM from microsoft. These are the quants that I like to use, that weren't uploaded to the main model by the ollama team.

tools 3.8b

272 Pulls 3 Tags Updated 9 months ago
olmoe-1b-7b-0924

An MoE model developed by allenai competitive with llama2

244 Pulls 5 Tags Updated 1 year ago
lucy

A compact model focused on agentic web search

tools 1.7b

201 Pulls 6 Tags Updated 3 months ago
exaone-4.0

LGAI has developed their latest version of the exaone model series, now with reasoning!

1.2b

194 Pulls 4 Tags Updated 2 months ago
gemma3

Google's new small model

270m 1b

131 Pulls 10 Tags Updated 4 months ago
gemma3n

Google's MatFormer addition to the gemma3 family

e2b

130 Pulls 6 Tags Updated 2 months ago
VibeThinker

tools

117 Pulls 2 Tags Updated 2 weeks ago
jamba-reasoning

A small and efficient reasoning model, with a hybrid transformer and mamba architecture

tools 3b

109 Pulls 4 Tags Updated 1 month ago
granite-embedding-english

Embedding models for English language, made by the IBM-Granite team, in 2 (small) sizes

embedding

86 Pulls 4 Tags Updated 11 months ago
deepseek-r1-qwen-distill

Useful DQ2 quants for deepseek-r1-qwen-distill:1.5b

1.5b

85 Pulls 6 Tags Updated 6 months ago
olmo2

Allen Institute's Latest tiny LLM in the Olmo family

1b

35 Pulls 6 Tags Updated 4 months ago
falcon-h1

1.5b

12 Pulls 5 Tags Updated 1 month ago
granite3.3

Additional quants of the granite3.3:2b model

tools 2b

6 Pulls 5 Tags Updated 4 months ago
tulu3

A model finetuned from llama3.1, developed by allenai

4 Pulls 6 Tags Updated 11 months ago
ministral:8b

This is the Ministral 8b model released by MistralAI. I've had some fun using it, and honestly find it to be really fast and smart for a model of this size. Hope you enjoy pulling it early through here! (ps- this is q4_K_S)