Gemma 3 4B · Ollama

joblesscoders/gemma3-math

Fintuned Gemma3:4B on math dataset #MathReasoning-mini

51 Pulls 1 Tag Updated 8 months ago

jayeshpandit2480/gemma3-UNCENSORED

These are essentially Completely UNCENSORED versions of GEMMA3 1B and 4B. Just NJOY!!!

vision 1b 4b

7,654 Pulls 2 Tags Updated 7 months ago

scb10x/typhoon2.1-gemma3-4b

Typhoon2.1 4B - 4B parameters Thai / English bilingual LLM build based on Gemma3.

tools

24.1K Pulls 1 Tag Updated 1 year ago

mshojaei77/gemma3persian

A 4B-parameter Persian-specialized language model built on Google's Gemma 3 architecture, fine-tuned on high-quality Persian text data while preserving multimodal capabilities for native-quality responses.

3,005 Pulls 1 Tag Updated 1 year ago

R4C3R/gemma-3-4b-it-heretic

Gemma-3-4B-IT fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.

725 Pulls 2 Tags Updated 1 month ago

HarshitPatil/daisy

Daisy is a personalized AI assistant built on Gemma 3 4B, fine-tuned with LoRA to provide a more helpful, friendly, and personalized conversational experience. It is designed for everyday assistance, coding help, research, learning, productivity tasks, an

tools

11 Pulls 1 Tag Updated 1 week ago

samuser3/Gemma-3-4B-VL-it-Gemini-Pro

Contact & Chat: https://etherpad.wikimedia.org/p/ollama

vision

348 Pulls 1 Tag Updated 4 months ago

Tharusha_Dilhara_Jayadeera/singemma

A Sinhala-adapted version of Google’s Gemma 3 4B, continually pre-trained on 10.7M Sinhala sentences with a custom 16k vocabulary using 4-bit LoRA.

214 Pulls 1 Tag Updated 11 months ago

julienp79/occitan-gemma-3-4b-it-rslora-sfttrainer

Gemma 3 4B Instruct fine-tuned on Occitan (Lengadocian) via RS-LoRA (r=32). Good balance of quality and speed. Q2_K to f16 quants.

9 Pulls 6 Tags Updated 3 months ago

etangaming123/mai

gemma3:4b but mai from bunny girl senpai [made for a schoolfriend] (info taken from https://aobuta.fandom.com/wiki/Mai_Sakurajima)

vision

122 Pulls 1 Tag Updated 12 months ago

etangaming123/raffina

gemma3:4b but raffina (info taken from https://puyonexus.com/wiki/Raffina)

vision

102 Pulls 1 Tag Updated 11 months ago

julienp79/occitan-gemma-3-4b-it-dora-sfttrainer

Gemma 3 4B Instruct fine-tuned on Occitan via DoRA (r=16). Lightweight model for resource-constrained setups. Q2_K, Q4_K_M, Q5_K_M, Q8_0, f16.

3 Pulls 6 Tags Updated 3 months ago

etangaming123/ruikamishiro

gemma3:4b but rui kamishiro (info taken from https://projectsekai.fandom.com/wiki/Kamishiro_Rui)

vision

3 Pulls 1 Tag Updated 5 months ago

boboba/Nidum-Gemma-3-4B-it-Uncensored-GGUF

https://huggingface.co/nidum/Nidum-Gemma-3-4B-it-Uncensored-GGUF

1,347 Pulls 1 Tag Updated 1 year ago

etangaming123/KAngel

gemma3:4b but KAngel (info taken from https://needy-streamer-overload.fandom.com/wiki/Ame-chan)

vision

236 Pulls 1 Tag Updated 1 year ago

fabriciocarraro/google-gemma-3-4b-it-gguf

Google Gemma-3-4B-it llama.cpp quantization by Fabrício Carraro

192 Pulls 1 Tag Updated 1 year ago

etangaming123/emuotori

gemma3:4b but Emu Otori (info taken from https://projectsekai.fandom.com/wiki/Otori_Emu)

vision

6 Pulls 1 Tag Updated 9 months ago

Lazysniper/HorizaEdu

An educational AI tutor based on Gemma 3 4B that provides clear, friendly study help while preventing cheating and inappropriate content.

vision

115 Pulls 1 Tag Updated 1 year ago

etangaming123/agaragarcookie

gemma3:4b but agar agar cookie (info taken from https://cookierunkingdom.fandom.com/wiki/Agar_Agar_Cookie)

vision

3 Pulls 1 Tag Updated 12 months ago

etangaming123/niko

gemma3:4b but niko (info taken from https://oneshot.fandom.com/wiki/Niko)

vision

6 Pulls 1 Tag Updated 1 year ago