Ollama - error
Hi,
I used your recommended command to run this on ollama: ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit = pulling manifest
Error: pull model manifest: 400: {"error":"Repository is not GGUF or is not compatible with llama.cpp"}
Hey, thanks for trying the model!
This is an MLX-format model optimized for Apple Silicon, so it's not directly compatible with Ollama (which requires GGUF/llama.cpp format). I'm removing the ollama tag to avoid confusion.
To run this model now:
pip install mlx-lm
mlx_lm.generate --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --prompt "Hello"
I'm working on a GGUF version that will support Ollama and LM Studio natively — will update here when it's available.
Update: The GGUF version is now live — this will work with Ollama:
ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF
👉 gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF
Available: Q4_K_M (2.7 GB), Q5_K_M (3.1 GB), Q8_0 (4.5 GB), F16 (8.3 GB).
Update: The GGUF version is now live! 🎉
ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF
Available quantizations: Q4_K_M (2.7 GB), Q5_K_M (3.1 GB), Q8_0 (4.5 GB), F16 (8.3 GB)
Closing this out — the GGUF repo is live, tested, and working with Ollama. Thanks for reporting!
ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF