Herding neural networks, not llamas🦙
-
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 thinking2,685 Pulls 1 Tag Updated 2 months ago
-
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 audio1,634 Pulls 1 Tag Updated 2 months ago
-
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 thinking1,394 Pulls 1 Tag Updated 2 months ago
-
gemma3n-e4b
Google Gemma 3n | Edge AI with tool support. Designed for consumer devices: efficient, local, tool-enabled
tools1,285 Pulls 1 Tag Updated 10 months ago
-
qwen3-coder-30b
Alibaba's Qwen3-Coder-30B 4bit with 256k token context. Enhanced tool calling for agentic coding tasks
tools thinking1,270 Pulls 1 Tag Updated 10 months ago
-
qwen3-coder-30b-1m
Alibaba's Qwen3-Coder-30B 4bit with 1M token context. Enhanced tool calling for agentic coding tasks
tools1,059 Pulls 1 Tag Updated 10 months ago
-
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 thinking941 Pulls 1 Tag Updated 2 months ago
-
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 thinking748 Pulls 1 Tag Updated 2 months ago
-
gemma4-31b-think
Gemma 4 31B (Google DeepMind) with thinking mode enabled. Best for complex reasoning, math, coding, and multi-step analysis. Knowledge cutoff: January 2025. Sampling: temperature 1.0 / top_p 0.95 / top_k 64.
vision tools thinking cloud474 Pulls 1 Tag Updated 2 months ago
-
gemma4-31b-fast
Gemma 4 31B (Google DeepMind) with thinking mode disabled. Best for quick questions, chat, and straightforward tasks. Knowledge cutoff: January 2025. Sampling: temperature 1.0 / top_p 0.95 / top_k 64.
vision tools thinking cloud412 Pulls 1 Tag Updated 2 months ago
-
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 audio402 Pulls 1 Tag Updated 2 months ago
-
gemma3n-e2b
Google Gemma 3n | Edge AI with tool support Designed for consumer devices: efficient, local, tool-enabled
tools177 Pulls 1 Tag Updated 10 months ago