mahdi sml

mahdisml's activity

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

New activity in Abiray/Nanbeige4.2-3B-GGUF 13 days ago

it will run in regular llamacpp ?

2

#1 opened 13 days ago by

mahdisml

New activity in thinkingmachines/Inkling 19 days ago

IT'S NOT FULLY OPEN - WEIGHT !

❤️👍 4

7

#9 opened 19 days ago by

mahdisml

New activity in WeiboAI/VibeThinker-3B about 1 month ago

very sensitive to quantization

1

#17 opened about 1 month ago by

J22

New activity in empero-ai/Qwythos-9B-Claude-Mythos-5-1M about 1 month ago

coding benchmark

👍 1

6

#2 opened about 1 month ago by

beyoru

New activity in unsloth/Qwen3.5-9B-MTP-GGUF about 1 month ago

Is using MTP actually slower?

👍 6

4

#4 opened 3 months ago by

jian2023

New activity in lmstudio-community/gemma-4-26B-A4B-it-GGUF about 2 months ago

How to use whit MTP?

2

#1 opened 3 months ago by

Lollo001lollo

New activity in unsloth/gemma-4-26B-A4B-it-qat-GGUF about 2 months ago

Unexpected Unsloth QAT Performance Compared to Unsloth IQ4_XS

👍 3

3

#3 opened about 2 months ago by

mahdisml

New activity in bartowski/tencent_Hunyuan-7B-Instruct-GGUF 12 months ago

wrong response

#3 opened 12 months ago by

mahdisml

New activity in bartowski/google_gemma-3-12b-it-GGUF over 1 year ago

IQ3_XXS use more VRAM

2

#5 opened over 1 year ago by

mahdisml

Q6_K vs Q6_K_L

6

#1 opened over 1 year ago by

mahdisml