Q4_K_M GGUF of a MedGemma health-chat fine-tune for local, private clinical AI prototyping.

Mellum2-12B-A2.5B-Instruct Q8_0 GGUF for Docker Model Runner (chat)

Mistral-Small-3.2-24B-Instruct Q4_K_M GGUF for Docker Model Runner (vision)

North Mini Code 1.0 UD-Q4_K_M GGUF for Docker Model Runner (chat)

Olmo 3.1 32B Instruct Q4_K_M GGUF for Docker Model Runner (chat)

ERNIE-4.5-21B-A3B-Thinking Q4_K_M GGUF for Docker Model Runner (chat)

LFM2.5-24B-A2B Q4_K_M GGUF for Docker Model Runner (chat)

GLM-4-9B-0414 Q4_K_M GGUF for Docker Model Runner (chat)

DeepSeek-Coder-V2-Lite-Instruct Q4_K_M GGUF for Docker Model Runner (chat)

MiMo-V2.6-Distill-Qwen-9B Q4_K_M GGUF for Docker Model Runner (chat)

GLM-4.6V-Flash Q4_K_M GGUF for Docker Model Runner (vision)

EmbeddingGemma 2 F16 GGUF for Docker Model Runner (embeddings)

DeepSeek-R1-Distill-Qwen-14B Q4_K_M GGUF for Docker Model Runner (chat)

AllThatToon webtoon image model (DDUF, fp16)

On-device Android agent that picks the next UI action. 2B, 1.3 GB.

Unlimited-OCR Q8_0 GGUF for Docker Model Runner (OCR)

Phi-4-mini-instruct Q4_K_M GGUF for Docker Model Runner (chat)

DeepSeek-OCR-2 Q8_0 GGUF for Docker Model Runner (OCR)

LFM2.5-8B-A1B Q4_K_M GGUF for Docker Model Runner (chat)

AllThatToon webtoon image model (DDUF, fp16)

Mellum2.1-12B-A2.5B-Thinking Q4_K_M GGUF for Docker Model Runner (chat)