Gen-4.5 · Ollama

bjoernb/gemma4-e4b-think

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.

vision tools thinking

842 Pulls 1 Tag Updated 4 months ago

mirage335/gpt-oss-120b-virtuoso

Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.

tools thinking

125 Pulls 1 Tag Updated 9 months ago

mirage335/gpt-oss-20b-virtuoso

Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.

tools thinking

125 Pulls 1 Tag Updated 9 months ago

bjoernb/gemma4-e4b-fast

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.

vision tools thinking

1,616 Pulls 1 Tag Updated 4 months ago

ProAdminGod/gemma3-tuned

A tuned version of Gemma3n with 4 active parameters and a total of 7. Works well on low power devices like raspberry pi 5 with 16GB of RAM

58 Pulls 1 Tag Updated 6 months ago

ShreyanGondaliya/gemma-4-claude-opus-4.6-thinking-s7-multimodal

Gemma 4 distilled from claude opus 4.6 thinking. Has only a 5% gap with claude opus 4.6 thinking while being over 40x smaller. Designed for server inference. Designed for local inference

tools thinking

622 Pulls 1 Tag Updated 4 months ago

bjoernb/gemma4-e2b-think

Gemma 4 E2B (Google DeepMind) with thinking mode enabled. Compact multimodal model — 2.3B effective / 5.1B total parameters. Supports text, image and audio input. Designed for edge devices and local deployment. Knowledge cutoff: January 2025.

vision tools thinking

480 Pulls 1 Tag Updated 4 months ago

Barbatos/gemfable-agent

Agentic coding model for 24 GB GPUs: TeichAI's Gemma-4-31B Fable-5 agent distill (vision + thinking + tools) with a disciplined coding-agent system prompt baked in. Inspect → reproduce → smallest fix → re-verify.

vision tools thinking 31b

143 Pulls 1 Tag Updated 1 month ago

midnightcoderagent/MidnightCoder-30B

**MidnightCoder-30B** coding model for the Midnight Coder Agent with SmartContext (~45% less prompt context). Install: `npm install -g midnight-coder` • Run: `ollama run midnightcoderagent/MidnightCoder-30B`

tools

9,280 Pulls 1 Tag Updated 1 month ago

rafw007/gemma4-26b-claude-coder

Niestandardowy model Gemma 4 26B (~25,8B parametrów), dostrojony do działania jako niezależny agent kodowania i administracji . Obsługuje API zgodne z Anthropic, dzięki czemu obsługuje Claude Code, Codex i Opencode

tools thinking

807 Pulls 1 Tag Updated 2 months ago

FableForge-AI/mythos-9b

Best all-rounder uncensored AI agent. 13.9/15 total score. Strong reasoning (4.5), tool use (4.6), censorship bypass (4.8). Trained on real Fable5 agent traces. 5GB, 16K context. Shell commands, code gen, multi-step reasoning. Apache 2.0.

305 Pulls 2 Tags Updated 1 month ago

dengcao/ERNIE-4.5-21B-A3B-PT

This model was converted to GGUF format from baidu/ERNIE-4.5-21B-A3B-PT using llama.cpp via the ggml.ai's GGUF-my-repo space.

679 Pulls 1 Tag Updated 1 year ago

dengcao/ERNIE-4.5-0.3B-PT

This model was converted to GGUF format from baidu/ERNIE-4.5-0.3B-PT using llama.cpp via the ggml.ai's GGUF-my-repo space.

687 Pulls 3 Tags Updated 1 year ago

carstenuhlig/omnicoder-9b

9B coding agent based on Qwen3.5-9B, fine-tuned on 425K real agentic traces from Claude Opus 4.6, GPT-5.4, and Gemini 3.1. Reads before it writes, traces bugs to the root cause, doesn't clobber your existing code.

tools thinking

15.9K Pulls 3 Tags Updated 5 months ago

nishtahir/sera

SERA is a state-of-the-art open-source coding agent that achieves 49.5% on SWE-bench Verified, matching the performance of frontier open models like Devstral-Small-2 (24B) and larger models like GLM-4.5-Air (110B)

tools thinking 8b 32b

333 Pulls 9 Tags Updated 6 months ago