Hugging Face's logo

DanCanCos
/
Overthinking-Rustacean-Behemoth_MLX_8

Text Generation
MLX
Safetensors
Transformers
Rust
English
qwen3
text-generation-inference
unsloth
reasoning
programming
code
coding
conversational
8-bit precision
Model card Files
xet
Community
  • 8bit MLX quant of Daemontatox/Overthinking-Rustacean-Behemoth
  • Created using mlx_lm v0.25.2
  • Uses corrected Qwen3 Jinja template to fix the "unable to parse template" error in LM Studio
Downloads last month
79
Safetensors
Model size
73B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DanCanCos/Overthinking-Rustacean-Behemoth_MLX_8

Base model

Qwen/Qwen3-32B
Finetuned
QuixiAI/Qwen3-72B-Embiggened
Finetuned
Daemontatox/OR1-Behemoth
Quantized
(5)
this model

Dataset used to train DanCanCos/Overthinking-Rustacean-Behemoth_MLX_8