DeepSeek-R1-Distill-MLX - a moot20 Collection

moot20 's Collections

DeepScaleR-1.5B-Preview

s1-32B

Velvet

Mistral-Small-24B-2501

Llama-3.1-Tulu-3

SmolVLM 256M & 500M

DeepSeek-R1-Distill-MLX

Phi-4

DeepSeek-R1-Distill-MLX

updated Feb 3

DeepSeek-R1-Distill model series - quantized and converted to MLX

moot20/DeepSeek-R1-Distill-Llama-8B-MLX-4bit

Text Generation • 1B • Updated Jan 27 • 9
moot20/DeepSeek-R1-Distill-Llama-8B-MLX-6bits

Text Generation • 2B • Updated Feb 3 • 9
moot20/DeepSeek-R1-Distill-Llama-8B-MLX-8bits

Text Generation • 2B • Updated Feb 3 • 6
moot20/DeepSeek-R1-Distill-Qwen-1.5B-MLX-4bit

Text Generation • 0.3B • Updated Jan 28 • 4
moot20/DeepSeek-R1-Distill-Qwen-1.5B-MLX-6bits

Text Generation • 0.4B • Updated Feb 3 • 3
moot20/DeepSeek-R1-Distill-Qwen-1.5B-MLX-8bits

Text Generation • 0.5B • Updated Feb 3 • 7
moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit

Text Generation • 1B • Updated Jan 28 • 4 • 1
moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-6bits

Text Generation • 2B • Updated Feb 3 • 5
moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-8bits

Text Generation • 2B • Updated Feb 3 • 7
moot20/DeepSeek-R1-Distill-Qwen-14B-MLX-4bit

Text Generation • 2B • Updated Jan 28 • 5
moot20/DeepSeek-R1-Distill-Qwen-14B-MLX-6bits

Text Generation • 3B • Updated Feb 3 • 9
moot20/DeepSeek-R1-Distill-Qwen-14B-MLX-8bits

Text Generation • 4B • Updated Feb 3 • 10
moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-4bits

Text Generation • 5B • Updated Feb 3 • 10
moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-6bits

Text Generation • 7B • Updated Feb 3 • 10
moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-8bits

Text Generation • 9B • Updated Feb 3 • 10