Bib Projects

bibproj's activity

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

New activity in mlx-community/GLM-5.2-DQ4plus-q8 8 days ago

config declares num_nextn_predict_layers=1 but MTP draft tensors were dropped (disables speculative decoding)

1

#4 opened 9 days ago by

WillMitchell

New activity in mlx-community/GLM-5.2-4bit 22 days ago

big thank you for providing this 4bit mlx.

🚀 1

1

#1 opened 22 days ago by

crystech

New activity in mlx-community/GLM-5.2-DQ4plus-q8 26 days ago

Garbage very soon in the output

👍 1

25

#3 opened about 1 month ago by

labhraighlep

New activity in CohereLabs/tiny-aya-global 28 days ago

Also providing MLX quants?

#6 opened 5 months ago by

bibproj

New activity in mlx-community/GLM-5.2-DQ4plus-q8 28 days ago

ValueError: Missing 285 parameters

7

#1 opened about 1 month ago by

finding1

How did you run this on 512GB mac studio?

2

#2 opened about 1 month ago by

jimreynold2nd

New activity in mlx-community/GLM-5.1-DQ4plus-q8 about 1 month ago

How does this style of quant stack up to the existing MXFP4 quant?

9

#1 opened about 1 month ago by

harfum8

New activity in mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8 about 2 months ago

Thanks

1

#1 opened 3 months ago by

labhraighlep

Vision capabilities are stripped

1

#2 opened 2 months ago by

harfum8

MLX models and disclosure

2

#3 opened about 2 months ago by

labhraighlep

New activity in mlx-community/MiniMax-M2.7-3bit 3 months ago

Low quality quant

4

#1 opened 3 months ago by

DaniDubi

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

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

1

#1 opened 5 months ago by

finding1

New activity in mlx-community/MiniMax-M2.5-8bit 5 months ago

5bit and 6bit versions

5

#1 opened 5 months ago by

darthsider

New activity in mlx-community/DeepSeek-V3.2-mlx-5bit 6 months ago

Quantization question

1

#1 opened 6 months ago by

Galathana

New activity in mlx-community/MiniMax-M2.1-3bit 6 months ago

Anyone running this with M4 Max 128gb? How does it compare to 4bit quantization?

5

#1 opened 7 months ago by

tumma72

New activity in sszymczyk/DeepSeek-V3.2-nolight-GGUF 6 months ago

Feedback

17

#1 opened 6 months ago by

bibproj

New activity in deepseek-ai/DeepSeek-V3.2 6 months ago

Running the model with a dense attention

4

#35 opened 7 months ago by

sszymczyk

New activity in mlx-community/GLM-4.7-8bit-gs32 6 months ago

Can the M2 Ultra Mac Pro with 192GB memory run this model?

23

#1 opened 7 months ago by

HanningLiu

New activity in mlx-community/MiniMax-M2.1-4bit 6 months ago

Template Think issue

3

#2 opened 7 months ago by

marutichintan

New activity in mlx-community/DeepSeek-V3.2-4bit 7 months ago

[SOLVED] No instruction following, Model just outputs vaguely relevant text, or goes into loops

5

#1 opened 8 months ago by

bibproj