noctrex

noctrex's activity

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

New activity in noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF 7 minutes ago

Poor performance and pretty lobotomized

1

#1 opened about 1 hour ago by

mancub

New activity in noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF 2 days ago

MXFP4 vs other 4-bit quant algos?

2

#3 opened 3 days ago by

dinerburger

New activity in noctrex/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-MXFP4_MOE-GGUF 4 days ago

can you please do an f16 version

1

#1 opened 4 days ago by

Shuasimodo

New activity in noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF 4 days ago

It would be neat to see a Heretical version of this.

1

#1 opened about 1 month ago by

SabinStargem

New activity in noctrex/MiroThinker-1.7-mini-MXFP4_MOE-GGUF 6 days ago

AI Model Evaluation Report: MiroThinker-1.7-Mini (GGUF/Ollama)

1

#1 opened 6 days ago by

phanthai12

New activity in noctrex/Huihui-Qwen3-VL-4B-Instruct-abliterated-GGUF 9 days ago

Would it make sense to get Qwen3-VL MXFP4 quants?

20

#2 opened about 2 months ago by

ampersandru

New activity in noctrex/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF 12 days ago

command to create GGUF MXFP4 mixed with BF16

1

#5 opened 13 days ago by

ghit72

New activity in noctrex/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF 17 days ago

It's really good.

👀 1

26

#3 opened 21 days ago by

Shuasimodo

New activity in noctrex/LFM2-24B-A2B-MXFP4_MOE-GGUF 19 days ago

Model performance

2

#1 opened 19 days ago by

spanspek

New activity in noctrex/Qwen3.5-122B-A10B-MXFP4_MOE-GGUF 19 days ago

Kind request for Qwen3.5-397B-A17B MXFP4 BF16

7

#2 opened 20 days ago by

dehnhaide

New activity in noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF 19 days ago

Increasing the precision of some of the weights when quantizing

👍 4

57

#2 opened 30 days ago by

Shuasimodo

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 20 days ago

Is there some helpful regex to offload all MoE layers to the CPU?

4

#7 opened 20 days ago by

hdnh2006

New activity in noctrex/Qwen3.5-122B-A10B-MXFP4_MOE-GGUF 20 days ago

BF16 version?

1

#1 opened 20 days ago by

Kackliqur

New activity in noctrex/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF 20 days ago

"Use this model" wrong tag by default.

👍 2

1

#2 opened 21 days ago by

jorj2

Qwen3.5-27B？

1

#4 opened 20 days ago by

wzgrx

New activity in noctrex/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF 21 days ago

Try a different model and/or config.

2

#1 opened 21 days ago by

E7Reine

New activity in noctrex/LightOnOCR-2-1B-GGUF 23 days ago

Embedded images?

2

#3 opened 24 days ago by

coder543

New activity in noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF 25 days ago

BF16 has looping issues

28

#4 opened 28 days ago by

jmander11

New activity in noctrex/LightOnOCR-2-1B-GGUF 25 days ago

Tried to use with llama-cpp-python without success

3

#1 opened about 2 months ago by

rriscoc

Infinite loop

3

#2 opened about 2 months ago by

kielCAC