Hugging Face's logo

majentik
/
Leanstral-RotorQuant-MLX-8bit

Text Generation
MLX
Safetensors
mistral3
rotorquant
kv-cache-quantization
8bit
weight-quantization
leanstral
lean4
formal-proofs
theorem-proving
quantized
apple-silicon
mistral
Mixture of Experts
8-bit precision
Model card Files
xet
 Community
majentik commited on
Commit
4e0de35
·
verified ·
1 Parent(s): 76d45b9

Remove links to retired card-only KV-docs repos

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -112,7 +112,6 @@ Leanstral excels at:
112
  ## See Also
113
 
114
  - [mistralai/Leanstral-2603](https://huggingface.co/mistralai/Leanstral-2603) -- Base model
115
- - [majentik/Leanstral-RotorQuant](https://huggingface.co/majentik/Leanstral-RotorQuant) -- Full-precision weights + RotorQuant KV cache
116
  - [majentik/Leanstral-RotorQuant-MLX-4bit](https://huggingface.co/majentik/Leanstral-RotorQuant-MLX-4bit) -- MLX 4-bit + RotorQuant
117
  - [majentik/Leanstral-RotorQuant-MLX-2bit](https://huggingface.co/majentik/Leanstral-RotorQuant-MLX-2bit) -- MLX 2-bit + RotorQuant
118
  - [majentik/Leanstral-TurboQuant-MLX-8bit](https://huggingface.co/majentik/Leanstral-TurboQuant-MLX-8bit) -- MLX 8-bit + TurboQuant
@@ -145,4 +144,4 @@ Leanstral excels at:
145
  | [TurboQuant](https://huggingface.co/majentik/leanstral-turboquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
146
  | [TurboQuant-MLX-2bit](https://huggingface.co/majentik/leanstral-turboquant-mlx-2bit) | mlx-lm | card-only | Apple Silicon, smallest |
147
  | [TurboQuant-MLX-4bit](https://huggingface.co/majentik/leanstral-turboquant-mlx-4bit) | mlx-lm | card-only | Apple Silicon balanced |
148
- | [TurboQuant-MLX-8bit](https://huggingface.co/majentik/leanstral-turboquant-mlx-8bit) | mlx-lm | card-only | Apple Silicon reference |
 
112
  ## See Also
113
 
114
  - [mistralai/Leanstral-2603](https://huggingface.co/mistralai/Leanstral-2603) -- Base model
 
115
  - [majentik/Leanstral-RotorQuant-MLX-4bit](https://huggingface.co/majentik/Leanstral-RotorQuant-MLX-4bit) -- MLX 4-bit + RotorQuant
116
  - [majentik/Leanstral-RotorQuant-MLX-2bit](https://huggingface.co/majentik/Leanstral-RotorQuant-MLX-2bit) -- MLX 2-bit + RotorQuant
117
  - [majentik/Leanstral-TurboQuant-MLX-8bit](https://huggingface.co/majentik/Leanstral-TurboQuant-MLX-8bit) -- MLX 8-bit + TurboQuant
 
144
  | [TurboQuant](https://huggingface.co/majentik/leanstral-turboquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
145
  | [TurboQuant-MLX-2bit](https://huggingface.co/majentik/leanstral-turboquant-mlx-2bit) | mlx-lm | card-only | Apple Silicon, smallest |
146
  | [TurboQuant-MLX-4bit](https://huggingface.co/majentik/leanstral-turboquant-mlx-4bit) | mlx-lm | card-only | Apple Silicon balanced |
147
+ | [TurboQuant-MLX-8bit](https://huggingface.co/majentik/leanstral-turboquant-mlx-8bit) | mlx-lm | card-only | Apple Silicon reference |