Mukul

mtcl's activity

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

New activity in nvidia/DeepSeek-V4-Pro-NVFP4 5 days ago

nvidia/DeepSeek-V4-flash-NVFP4

4

#1 opened 6 days ago by

mtcl

New activity in canada-quant/DeepSeek-V4-Flash-NVFP4-FP8-MTP 5 days ago

Docker Image

5

#1 opened 6 days ago by

mtcl

New activity in unsloth/DeepSeek-V4-Flash 6 days ago

Worse than (smaller) MiniMax M2.7??

17

#2 opened about 1 month ago by deleted

New activity in deepseek-ai/DeepSeek-V4-Flash 24 days ago

Unable to run on 2x RTX Pro 6000 (DEEP_GEMM problem)

➕ 10

17

#15 opened about 1 month ago by

stev236

New activity in mistralai/Mistral-Medium-3.5-128B 29 days ago

Running on 2 RTX Pro 6000 Blackwell GPUs at ~30 tps (Instructions that worked for me)

👍❤️ 7

10

#17 opened about 1 month ago by

CarouselAether

New activity in RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 29 days ago

2x Nvidia 6000 Pros

3

#2 opened about 1 month ago by

mtcl

New activity in lukealonso/MiMo-V2.5-NVFP4 about 1 month ago

Will it work on 2X6000 Pros

6

#1 opened about 1 month ago by

mtcl

New activity in Intel/DeepSeek-V4-Flash-W4A16-AutoRound about 1 month ago

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

9

#1 opened about 1 month ago by

marshal007

New activity in nvidia/MiniMax-M2.7-NVFP4 about 1 month ago

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

3

#2 opened about 1 month ago by

mtcl

New activity in ubergarm/Kimi-K2.6-GGUF about 1 month ago

really awesome speeds! running at 256k context.

🔥 1

5

#11 opened about 1 month ago by

mtcl

New activity in Qwen/Qwen3.6-27B about 1 month ago

MOE 122b and 397b please!

🚀 24

14

#7 opened about 1 month ago by

jesleocizi

New activity in ubergarm/Kimi-K2.6-GGUF about 1 month ago

How to disable thinking?

4

#9 opened about 1 month ago by

Hansi2024

New activity in demon-zombie/MiniMax-M2.7-AWQ-4bit about 1 month ago

These are NOT actual AWQ-quantized models.

2

#1 opened about 2 months ago by

cai-cai

New activity in NinjaBoffin/MiniMax-M2.7-NVFP4 about 1 month ago

max context

#2 opened about 1 month ago by

mtcl

New activity in ubergarm/Kimi-K2.6-GGUF about 1 month ago

No think tags.

10

#4 opened about 1 month ago by

DrRos

New activity in nvidia/MiniMax-M2.5-NVFP4 about 1 month ago

Minimax M2.7 NVFP4

👀🔥 5

4

#4 opened about 2 months ago by

mtcl

New activity in lukealonso/MiniMax-M2.7-NVFP4 about 1 month ago

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

3

#9 opened about 1 month ago by

mtcl

New activity in lukealonso/MiniMax-M2.7-NVFP4 about 2 months ago

w1 not matching w3 weight scales

12

#1 opened about 2 months ago by

dareposte

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

1

#5 opened about 2 months ago by

mtcl

New activity in MiniMaxAI/MiniMax-M2.7 about 2 months ago

Minimax 2.7 !!!!

👍 5

3

#3 opened about 2 months ago by

mtcl