veg

ciprianv's activity

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

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 7 days ago

Cant get it to work on 8x RTX3090

14

#1 opened 16 days ago by

maglat

New activity in lukealonso/MiniMax-M2.5-NVFP4 8 days ago

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

👍 1

20

#2 opened 17 days ago by

zenmagnets

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 12 days ago

accuracy

17

#4 opened 16 days ago by

ktsaou

New activity in mratsim/MiniMax-M2.1-BF16-INT4-AWQ 16 days ago

Fastest for my 3090x8

2

#1 opened 17 days ago by

ciprianv

New activity in 0xSero/MiniMax-M2.1-REAP-40 about 2 months ago

Hey i like the model could you maybe make a NVFP4 version or a version optimised for the dgx spark?

3

#1 opened about 2 months ago by

Floris111

New activity in cerebras/GLM-4.7-REAP-218B-A32B about 2 months ago

Please create also Minimax 2.1 REAP versions

2

#1 opened about 2 months ago by

ciprianv

New activity in unsloth/MiniMax-M2.1-GGUF about 2 months ago

Report: getting 20 t/s with UD-Q4_K_XL and 72 VRAM

🔥 1

10

#2 opened 2 months ago by

SlavikF

New activity in unsloth/MiniMax-M2.1-GGUF 2 months ago

Hot Damn This Model Cooks!

👍 6

12

#5 opened 2 months ago by

aaron-newsome

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

Please make 4 bit dwq mlx quant

2

#1 opened 2 months ago by

Narutoouz

New activity in unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF 3 months ago

Please update llama.cpp to see improved performance!

🚀 4

4

#7 opened 3 months ago by

danielhanchen

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF 7 months ago

Updated Title: UDQ4_K_XL - Great Rust coder

👍 3

5

#11 opened 7 months ago by

wonderfuldestruction

New activity in unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF 7 months ago

download link creates Q5_K_M instead of UD-Q5_K_XL named files

1

#2 opened 7 months ago by

ciprianv

New activity in Qwen/Qwen3-Coder-480B-A35B-Instruct 7 months ago

Confused about the eval score

❤️ 2

3

#15 opened 7 months ago by

Denisssy

New activity in ubergarm/DeepSeek-TNG-R1T2-Chimera-GGUF 8 months ago

IQ3_KS metrics on mixed CUDA + CPU, pretty good model!

🔥 2

34

#2 opened 8 months ago by

Panchovix

New activity in tngtech/DeepSeek-TNG-R1T2-Chimera 8 months ago

What are the recommended settings?

1

#7 opened 8 months ago by

ciprianv

New activity in ubergarm/DeepSeek-R1-0528-GGUF 8 months ago

Thanks for your work! Any chance for something between Q2_K_R and Q3_K_R?

👍 👀 5

19

#7 opened 9 months ago by

Panchovix

New activity in unsloth/DeepSeek-R1-0528-GGUF 9 months ago

Update - Tool Calling + Chat Template bug fixes

9

#20 opened 9 months ago by

danielhanchen

Please share feedback here!

34

#6 opened 9 months ago by

shimmyshimmer

New activity in ubergarm/DeepSeek-R1-0528-GGUF 9 months ago

Recommendation for 256 ram 48 vram

❤️ 2

5

#2 opened 9 months ago by

ciprianv

New activity in ubergarm/Qwen3-235B-A22B-GGUF 10 months ago

Q6 K

36

#1 opened 10 months ago by

Autumnlight