Mukul

mtcl's activity

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

New activity in Intel/DeepSeek-V4-Flash-W4A16-AutoRound about 19 hours ago

Can I deploy it with sglang at my 8*4090 ubuntu sever?

3

#1 opened 1 day ago by

marshal007

New activity in nvidia/MiniMax-M2.7-NVFP4 about 24 hours ago

Context Length for 2X6000 Pros (2x96 = 192GB VRAM)

2

#2 opened 4 days ago by

mtcl

New activity in unsloth/DeepSeek-V4-Flash 4 days ago

Worse than (smaller) MiniMax M2.7??

13

#2 opened 4 days ago by deleted

New activity in ubergarm/Kimi-K2.6-GGUF 4 days ago

really awesome speeds! running at 256k context.

🔥 1

5

#11 opened 5 days ago by

mtcl

New activity in Qwen/Qwen3.6-27B 4 days ago

MOE 122b and 397b please!

🚀 16

8

#7 opened 6 days ago by

jesleocizi

New activity in ubergarm/Kimi-K2.6-GGUF 5 days ago

How to disable thinking?

4

#9 opened 5 days ago by

Hansi2024

New activity in demon-zombie/MiniMax-M2.7-AWQ-4bit 7 days ago

These are NOT actual AWQ-quantized models.

2

#1 opened 14 days ago by

cai-cai

New activity in NinjaBoffin/MiniMax-M2.7-NVFP4 7 days ago

max context

#2 opened 7 days ago by

mtcl

New activity in ubergarm/Kimi-K2.6-GGUF 7 days ago

No think tags.

10

#4 opened 7 days ago by

DrRos

New activity in nvidia/MiniMax-M2.5-NVFP4 9 days ago

Minimax M2.7 NVFP4

👀🔥 5

4

#4 opened 15 days ago by

mtcl

New activity in lukealonso/MiniMax-M2.7-NVFP4 9 days ago

Unable to use full 192k context in SGLang with MiniMax-M2.7-NVFP4 (runtime capped at ~80,964 tokens)

3

#9 opened 9 days ago by

mtcl

New activity in lukealonso/MiniMax-M2.7-NVFP4 12 days ago

w1 not matching w3 weight scales

12

#1 opened 16 days ago by

dareposte

New activity in lukealonso/MiniMax-M2.7-NVFP4 15 days ago

tokenizer component mismatch and w1_weight_scale_2 must match w3_weight_scale_2. Accuracy may be affected issue

1

#5 opened 15 days ago by

mtcl

New activity in MiniMaxAI/MiniMax-M2.7 17 days ago

Minimax 2.7 !!!!

👍 5

3

#3 opened 17 days ago by

mtcl

New activity in MiniMaxAI/MiniMax-M2.5 18 days ago

Where is M2.7 ??

6

#58 opened 19 days ago by

mtcl

New activity in ubergarm/GLM-5.1-GGUF 21 days ago

Fantastic as usual

❤️ 5

5

#1 opened 21 days ago by

ndroidph

New activity in google/gemma-4-31B-it 26 days ago

vllm / sglang support?

👍 11

7

#4 opened 26 days ago by

mtcl

liked a model 29 days ago

nvidia/MiniMax-M2.5-NVFP4

Text Generation • 116B • Updated 11 days ago • 70.5k • 33

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 about 1 month ago

Searching for a new Tool Parser

3

#15 opened about 1 month ago by

LucasMM14

VLLM + MTP + NVFP4 doesn't work

👀 1

2

#16 opened about 1 month ago by

catplusplus