Gemma 3 1B · Ollama

ttempvnn/aifeifei798-Gemma-4-Queen-31B-it-uncensored-heretic-Q4-K-M

297 Pulls 1 Tag Updated 4 weeks ago

byczech/gemma4-it-16G-Q3_K_S

Gemma 4 31B text-only instruct model with tool-calling and thinking support, quantized to Q3_K_S and optimized for 16 GB VRAM. Supports up to 256K context, with approximately 64K tokens fitting fully within 16 GB VRAM in tested configurations.

tools thinking 31b

57 Pulls 1 Tag Updated 3 weeks ago

rlaglovesme/luminar

Luminar is an advanced conversational engine built on Gemma 4 31B, optimized for dynamic persona roleplay, authentic instant messaging, with 262k context length.

cloud

35 Pulls 1 Tag Updated 2 weeks ago

SiliconBasedWorld/Gemma-4-31B-JANG_4M-CRACK

tools thinking

2,965 Pulls 5 Tags Updated 4 months ago

nayakaazkabiantara/Ellie

A Gemma 4 31B customized to have context7 MCP support and friendly and gen z like response

cloud

25 Pulls 1 Tag Updated 3 weeks ago

tinyrick/Gemma-4-Harmonia-31B-uncensored-heretic-vision-llmfan46

vision tools thinking

472 Pulls 1 Tag Updated 2 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

457 Pulls 5 Tags Updated 2 months ago

bjoernb/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 cloud

616 Pulls 1 Tag Updated 4 months ago

bjoernb/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 cloud

553 Pulls 1 Tag Updated 4 months ago

byczech/gemma4-it-mmproj-16G-Q3_K_S

Gemma 4 31B multimodal instruct model with vision support, quantized to Q3_K_S and optimized for 16 GB VRAM. Supports a practical context window of approximately 36K–40K tokens, depending on the Ollama version, GPU, backend and runtime configuration.

vision tools thinking 31b

242 Pulls 1 Tag Updated 4 days ago

Jarcgon/Gemma-4-31B-it-abliterated-Q4_K_M

378 Pulls 1 Tag Updated 3 months ago

edtorre/gemma4-31b-hermes

Gemma 4 31B (Q4_0) optimized for Hermes Agent — 64K context, 8192 max tokens, flash attention + Q8 KV cache. Fits 24 GB VRAM with optimizations.

vision tools thinking

151 Pulls 1 Tag Updated 1 month 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

134 Pulls 1 Tag Updated 1 month ago

jetelain/Gemma-4-31B

Gemma-4-31B UD-Q4_K_XL MTP from Unsloth

vision tools thinking

148 Pulls 1 Tag Updated 1 month ago

htdevs/phinegpt

PhineGPT is a custom AI assistant model built on top of Gemma4 31B using Ollama. It is designed as a general-purpose assistant optimized for accuracy, structured reasoning, and developer-friendly output.

vision tools thinking

62 Pulls 1 Tag Updated 4 months ago