TheCluster/Gemma-4-26B-A4B-MLX-mixed-7bit
Image-Text-to-Text • 27B • Updated
Artem K.
TheCluster
AI & ML interests
None yet
Recent Activity
updated a model about 4 hours ago
TheCluster/Gemma-4-26B-A4B-MLX-mixed-7bit published a model about 4 hours ago
TheCluster/Gemma-4-26B-A4B-MLX-mixed-7bit reacted to danielhanchen's post with 🔥 about 7 hours ago
You can now fine-tune Gemma 4 for free with our notebooks! 🔥
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
Organizations
TheCluster/Gemma-4-31B-Heretic-MLX-bf16
Image-Text-to-Text • 33B • Updated • 361
TheCluster/Gemma-4-26B-A4B-Heretic-MLX-7bit
Image-Text-to-Text • 27B • Updated • 538
TheCluster/Gemma-4-31B-Heretic-MLX-8bit
Image-Text-to-Text • 33B • Updated • 624 • 1
TheCluster/Gemma-4-31B-Heretic-MLX-mxfp4
Image-Text-to-Text • 33B • Updated • 434
TheCluster/Gemma-4-26B-A4B-Heretic-MLX-mxfp4
Image-Text-to-Text • 27B • Updated • 793
TheCluster/Gemma-4-26B-A4B-Heretic-MLX-9bit
Image-Text-to-Text • 27B • Updated • 472
TheCluster/Gemma-4-26B-A4B-Heretic-MLX-bf16
Image-Text-to-Text • 27B • Updated • 653 • 1
TheCluster/Gemma-4-26B-A4B-Heretic-MLX-8bit
Image-Text-to-Text • 27B • Updated • 643
TheCluster/Qwen3.5-27B-Heretic-MLX-8bit
Image-Text-to-Text • 27B • Updated • 403
TheCluster/Qwen3.5-27B-Heretic-MLX-mxfp8
Image-Text-to-Text • 27B • Updated • 364
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-9bit
Image-Text-to-Text • 35B • Updated • 991 • 2
TheCluster/Qwen3.5-27B-Heretic-MLX-mixed-v1
Image-Text-to-Text • 27B • Updated • 234 • 1
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-8bit
Image-Text-to-Text • 35B • Updated • 525
TheCluster/Qwen3.5-122B-A10B-Heretic-v2-MLX-mxfp8
Image-Text-to-Text • 122B • Updated • 572 • 1
TheCluster/Qwen3.5-27B-Heretic-MLX-bf16
Image-Text-to-Text • 27B • Updated • 1.24k • 2
TheCluster/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8
Image-Text-to-Text • 35B • Updated • 2.05k • 3
TheCluster/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MLX-mxfp4
Image-Text-to-Text • 35B • Updated • 5.61k • 9
TheCluster/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-MLX-bf16
Image-Text-to-Text • 2B • Updated • 754
TheCluster/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-MLX-8bit
Image-Text-to-Text • 27B • Updated • 1.46k
TheCluster/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-8bit
Image-Text-to-Text • 9B • Updated • 1.27k • 2
TheCluster/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-mxfp4
Image-Text-to-Text • 9B • Updated • 2.54k • 5
TheCluster/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-MLX-mxfp4
Image-Text-to-Text • 27B • Updated • 1.2k • 1
TheCluster/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8
Image-Text-to-Text • 9B • Updated • 1.54k • 2
TheCluster/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8
Image-Text-to-Text • 27B • Updated • 653 • 1
TheCluster/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8
Image-Text-to-Text • 9B • Updated • 11.4k • 11
TheCluster/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-bf16
Image-Text-to-Text • 9B • Updated • 768
TheCluster/Qwen3.5-9B-Ultra-Heretic-MLX-mxfp8
Image-Text-to-Text • 9B • Updated • 556 • 2
TheCluster/Crow-9B-HERETIC-4.6-MLX-8bit
Image-Text-to-Text • 9B • Updated • 149
TheCluster/Crow-9B-HERETIC-4.6-MLX-mxfp4
Image-Text-to-Text • 9B • Updated • 159