Downloads · 30 days
4
2% of all-time downloads
lfm2-5-8b-a1b-mlx-4bit-dequant-bf16
exolabs/lfm2-5-8b-a1b-mlx-4bit-dequant-bf16
lfm2-5-8b-a1b-mlx-4bit-dequant-bf16 is a machine learning model from exolabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Private dequantized BF16 export for vLLM validation.
All-time downloads
217
Public
Parameters
8.5B
33.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.9 GB · 100%
Parameter types
How the weights are stored.
BF168.5B · 100%
Model card
From the Hugging Face model README
exolabs/lfm2-5-8b-a1b-mlx-4bit-dequant-bf16
Private dequantized BF16 export for vLLM validation.
- Internal model id:
lfm2-5-8b-a1b-mlx-4bit - MLX source:
LiquidAI/LFM2.5-8B-A1B-MLX-4bit - Original HF comparison model:
LiquidAI/LFM2.5-8B-A1B - Export dtype:
bfloat16 - Text-only export:
False
This checkpoint is the result of dequantizing the quantized MLX checkpoint. It is not the original upstream BF16 checkpoint.
- Type
- lfm2_moe
- License
- other
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026