Finding 1

finding1's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in mlx-community/Qwen3.5-397B-A17B-8bit 5 days ago

Was this created with the fixes in mlx-lm version 0.30.8?

1

#1 opened 5 days ago by

finding1

New activity in meituan-longcat/LongCat-Flash-Chat 6 months ago

What sampler settings were used to achieve the reported benchmark scores?

👀 1

2

#8 opened 6 months ago by

finding1

New activity in NexVeridian/Qwen3-0.6B-8bit 6 months ago

Is this upload motivated by known problems in older 8-bit MLX quants of Qwen3-0.6B?

#1 opened 6 months ago by

finding1

New activity in mlx-community/ERNIE-4.5-300B-A47B-PT-4bit 6 months ago

Q8 version please

2

#2 opened 7 months ago by

acediac

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF 9 months ago

Llama 4 GGUFs now with multimodal (image) capabilities.

9

#5 opened 9 months ago by

shimmyshimmer

New activity in mradermacher/DeepSeek-V3-Base-GGUF 9 months ago

Q4_K_M missing blk.8.ffn_up_exps.weight

1

#1 opened 9 months ago by

finding1

Q4_K_M missing blk.8.ffn_up_exps.weight

1

#1 opened 9 months ago by

finding1