Gemma 4 4.5B · Ollama

4skl/gemma4-e4b-mtp

Multimodal 4.5B Gemma 4 with Unsloth Dynamic QAT & MTP (5.3GB). Features near-lossless vision, audio, text reasoning, an active 4-token speculative window, and an expanded 64K context size. Best for edge execution on systems with 8GB to 16GB RAM.

vision tools thinking

816 Pulls 1 Tag Updated 1 month 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

1,652 Pulls 1 Tag Updated 5 months ago

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

847 Pulls 1 Tag Updated 5 months ago

bjoernb/gemma4-e2b-fast

Gemma 4 E2B (Google DeepMind) with thinking mode disabled. 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

1,908 Pulls 1 Tag Updated 5 months ago

odytrice/gemma4

Gemma 4 Ollama profiles for RTX 4090/5090 across 12B, 26B-A4B, and 31B variants, with multimodal support and native tool calling

vision tools thinking

487 Pulls 5 Tags Updated 3 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

495 Pulls 1 Tag Updated 5 months ago

bjoernb/gemma4-26b-think

Gemma 4 26B MoE (Google DeepMind) with thinking mode enabled. Mixture-of-Experts — 25.2B total / 3.8B active parameters, 256K context. Supports text and image input. Knowledge cutoff: January 2025.

vision tools thinking

2,776 Pulls 1 Tag Updated 5 months 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

850 Pulls 1 Tag Updated 3 months ago

bjoernb/gemma4-26b-fast

Gemma 4 26B MoE (Google DeepMind) with thinking mode disabled. Mixture-of-Experts — 25.2B total / 3.8B active parameters, 256K context. Supports text and image input. Knowledge cutoff: January 2025.

vision tools thinking

1,071 Pulls 1 Tag Updated 5 months ago

mannix/gemma4-98e-v5-coder

Pruned to 98 experts gemma-4 a4b 26b v5-coder. Best 20b coder model overall

tools thinking

469 Pulls 31 Tags Updated 3 months ago

satgeze/gemma4-12b-uncensored-1.5m

Gemma 4 12B uncensored, 1.5M max context: certified 10/10 to 1.31M on a 32GB card. Vision included.

vision tools thinking

4,116 Pulls 1 Tag Updated 2 months ago

dcarrascosa/medgemma-1.5-4b-it

This repo packages Google’s google/medgemma-1.5-4b-it (MedGemma 1.5, 4B, instruction-tuned, multimodal) for Ollama, exposing vision + text inference and common Ollama features (structured JSON output, tool calling via your app, etc.)

vision

2,228 Pulls 3 Tags Updated 6 months ago