gemma · Ollama

Gemma 4 E2B fine-tuned for microscopy ID — rich 4-section scientific descriptions (genus + morphology + habitat + ID cues). Same 3.4 GB as v2, runs offline on laptop / phone. Apache 2.0. Research model — not a medical device.

vision tools thinking audio

10 Pulls 1 Tag Updated 2 days ago

supergoatscriptguy/mythos-sec

Security-focused local LLM. huihui-4 8B (Gemma-4 abliterated, native thinking) with a hardened system prompt for CTF, bug bounty, pentest methodology, and vulnerability research. Concise, direct, no disclaimers, no refusals. Apache 2.0.

vision tools thinking 8b

256 Pulls 2 Tags Updated 4 days ago

cabelleira/gemma4

tools

16 Pulls 1 Tag Updated 4 days ago

brinzaengineeringai/microlens-v2

Gemma 4 E2B fine-tuned on 122k microscopy VQA · 145+ genera · 5 categories · runs offline on a sub-$100 phone · Unsloth + llama.cpp · Apache 2.0 · research/educational only, not a medical device

vision

4 Pulls 1 Tag Updated 4 days ago

abdallazain2004/therapist-gemma

1 Pull 1 Tag Updated 6 days ago

nat_wan/Little-Gemma

2 Pulls 1 Tag Updated 6 days ago

aratan/gemma-4-E4B-q8-it-heretic

Modelo sin censura, muy rapido Q8 que es bastante

tools thinking

125 Pulls 1 Tag Updated 1 week ago

aratan/gemma4-e4b-SecOps

tools thinking

10 Pulls 1 Tag Updated 1 week ago

ggozad/prometheus2

Prometheus 2 (7B, Q4_K_M) — an LLM-as-judge model fine-tuned for absolute and pairwise grading of generative outputs.

15 Pulls 1 Tag Updated 1 week ago