Stronger Gemma 4 E4B coding agent for Claude Code, 64K context, native tool-calling, runs fully local on 16GB Apple Silicon.
3,704 Pulls 1 Tag Updated 2 months ago
Gemma 4 E4B (Google DeepMind) with thinking mode disabled. Compact multimodal model — 4.5B effective / 8B total parameters. Supports text, image and audio input. Designed for edge devices and local deployment. Knowledge cutoff: January 2025.
1,569 Pulls 1 Tag Updated 4 months ago
Gemma 4 E4B (Google DeepMind) with thinking mode enabled. Compact multimodal model — 4.5B effective / 8B total parameters. Supports text, image and audio input. Designed for edge devices and local deployment. Knowledge cutoff: January 2025.
821 Pulls 1 Tag Updated 4 months ago
Fine-tune of Gemma 4 E4B (4B parameters) specialized in offensive and defensive cybersecurity. Trained with LoRA (r=16) on a dataset covering vulnerability analysis, secure code review, and Java insecure code remediation.
577 Pulls 1 Tag Updated 3 months ago
Gemma 4 E4B admin and devops agent for Claude Code, 32K context fully on GPU for stable throughput, native tool-calling, runs local on 16GB Apple Silicon.
409 Pulls 1 Tag Updated 2 months ago
A modality-stripped variant of google/gemma-4-E4B-it for text-only classification, entity extraction, and structured-memory extraction. The vision encoder (150M params) and audio encoder (300M params) are removed; the text path is unchanged.
296 Pulls 3 Tags Updated 2 months ago
SwayAlgo Finance Gemma 4 E4B-it 1 is a Q4_K_M GGUF finance assistant for Indian business, accounting, reasoning, and finance MCQ tasks.
11 Pulls 1 Tag Updated 1 week ago
BibleAI is a production-ready Gemma 4 E4B model specialized for Bible study, theology, church history, and faith-centered Q&A.
445 Pulls 2 Tags Updated 3 months ago
A fine-tuned Gemma 4 E4B model for Bible study. Quotes Scripture precisely from the BSB, provides Greek/Hebrew word studies, and presents Protestant, Catholic, and Orthodox perspectives.
338 Pulls 1 Tag Updated 4 months ago
Offline cultivation intelligence — Gemma 4 E4B with Crowe Logic identity overlay for commercial and at-home mushroom growers. Built for the Gemma 4 Good Hackathon.
45 Pulls 1 Tag Updated 2 months ago
Fine-tuned Gemma 4 E4B for quality-checking Bethesda/Starfield game string translations. Detects 16 issue codes: tag mismatches, source-language leak, English leak, AI artifacts, repetition, truncation, and more.
11 Pulls 1 Tag Updated 2 months ago
LoRA adapter on Gemma 4 E4B for 3D print job planning. The first successful fine-tune after v1 (which parroted a template). This is the non-QAT sibling of the recommended v3 QAT model.
7 Pulls 1 Tag Updated 1 month ago
192 Pulls 1 Tag Updated 2 weeks ago
Abliterated (decensored) version of google/gemma-4-E4B-it, created using Heretic v1.2.0 with Arbitrary-Rank Ablation (ARA) and row-norm preservation.
12.3K Pulls 5 Tags Updated 4 months ago
https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF/resolve/main/gemma-4-E4B-it-ultra-uncensored-heretic-Q4_K_M.gguf
2,840 Pulls 1 Tag Updated 1 month ago
coder3101/gemma-4-E4B-it-heretic
1,478 Pulls 5 Tags Updated 1 month ago
4-bit K-quntized version of google/gemma-4-E4B-it. Generated using llama.cpp
2,707 Pulls 1 Tag Updated 4 months ago
979 Pulls 3 Tags Updated 2 months ago
Uncensored on-device finetune of google/gemma-4-E4B-it by the Chromia and Eval Engine team
1,012 Pulls 1 Tag Updated 2 months ago
A structurally extracted, text-only iteration of Google's multimodal gemma-4-E4B-it model. Vision and audio encoders have been fully decoupled to minimize VRAM footprint for text-centric workloads. System Prompt to address lost abilities.
556 Pulls 1 Tag Updated 3 months ago