Mukul

mtcl's activity

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

New activity in Sehyo/Qwen3.5-122B-A10B-NVFP4 about 7 hours ago

Failures on DGX Spark under vLLM

6

#9 opened 1 day ago by

Adrian1234

New activity in Sehyo/Qwen3.5-122B-A10B-NVFP4 2 days ago

Running command?

👍 1

6

#2 opened 6 days ago by

bhat1

MTP Added - Re-download

🚀 1

5

#7 opened 2 days ago by

Sehyo

New activity in Sehyo/Qwen3.5-122B-A10B-NVFP4 4 days ago

1M context

3

#3 opened 5 days ago by

mtcl

New activity in lukealonso/MiniMax-M2.5-NVFP4 12 days ago

"w1_weight_scale_2 must match w3_weight_scale_2. Accuracy may be affected."

👍 1

20

#2 opened 18 days ago by

zenmagnets

liked a model 14 days ago

lukealonso/MiniMax-M2.5-NVFP4

130B • Updated 15 days ago • 68.9k • 35

New activity in mlx-community/Qwen3.5-397B-A17B-nvfp4 15 days ago

I wish it would fit in 2x6000 PRO!

1

#2 opened 15 days ago by

mtcl

New activity in manu02/kani-tts-2-en-bnb-4bit-nf4-dq 15 days ago

OpenAI Compatible Server

#1 opened 15 days ago by

mtcl

New activity in tacos4me/Step-3.5-Flash-NVFP4 16 days ago

SGLang

2

#1 opened 16 days ago by

mtcl

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 17 days ago

accuracy

17

#4 opened 17 days ago by

ktsaou

FP8 + INT4 version

14

#2 opened 18 days ago by

bigstorm

New activity in Kebob/DeepSeek-V3.2-CPU-NUMA2-AMXINT4 30 days ago

NUMA

1

#2 opened 30 days ago by

mtcl

New activity in cyankiwi/GLM-4.7-REAP-268B-A32B-AWQ-4bit about 1 month ago

Thank you!

🤗 1

3

#1 opened about 1 month ago by

mtcl

New activity in cyankiwi/GLM-4.7-REAP-218B-A32B-AWQ-4bit about 1 month ago

Will you make the 268B version of this model ?

👍 2

2

#1 opened about 1 month ago by

mtcl

New activity in cerebras/GLM-4.7-REAP-268B-A32B-FP8 about 1 month ago

mtp

4

#1 opened about 2 months ago by

festr2

New activity in 0xSero/GLM-4.7-REAP-218B-A32B-W4A16 about 2 months ago

GLM-4.7-REAP-268B-A32B

#1 opened about 2 months ago by

mtcl

New activity in ubergarm/DeepSeek-V3.2-Speciale-GGUF about 2 months ago

Say Whattt?!

🔥 👍 4

7

#1 opened about 2 months ago by

mtcl

New activity in ubergarm/GLM-4.7-GGUF about 2 months ago

Stable run on 2x RTX 5090 and 2 Xeon E5 2696 V4 and DDR4 with ik_llama.cpp - 6.1 t/s on IQ4_K and 5.1 t/s on IQ5_K, opencode works with this

👍 1

17

#5 opened 2 months ago by

martossien

New activity in QuantTrio/GLM-4.7-AWQ about 2 months ago

Once again Thanks, here is my review for 8 x RTX 5090 setup

17

#2 opened 2 months ago by

crystech

New activity in QuantTrio/MiniMax-M2.1-AWQ 2 months ago

Thank you for your Quant!

👀 3

7

#1 opened 2 months ago by

mtcl