599 26 334

Michael Han

shimmyshimmer

https://unsloth.ai

AI & ML interests

None yet

Recent Activity

new activity about 18 hours ago

unsloth/GLM-4.7-Flash-GGUF:Infinite thinking (after </thinking> tag with updated quants

new activity about 18 hours ago

unsloth/GLM-4.7-Flash-GGUF:Ollama Support

new activity 2 days ago

unsloth/GLM-4.7-Flash-GGUF:High CPU Usage / Slow Context Processing

View all activity

Organizations

New activity in unsloth/GLM-4.7-Flash-GGUF about 18 hours ago

Infinite thinking (after </thinking> tag with updated quants

#14 opened 1 day ago by

CoruNethron

Ollama Support

#15 opened about 24 hours ago by

yqchen-sci

New activity in unsloth/GLM-4.7-Flash-GGUF 2 days ago

High CPU Usage / Slow Context Processing

➕ 👍 10

#5 opened 6 days ago by

PussyHut

New activity in unsloth/GLM-4.7-Flash-GGUF 5 days ago

Jan 21: GGUFs all UPDATED!!!

🤗 ❤️ 5

#1 opened 6 days ago by

danielhanchen

Kind of broken.

#7 opened 6 days ago by

ItzPingCat

New activity in unsloth/LTX-2-GGUF 6 days ago

New Sample Workflow!!

#7 opened 6 days ago by

shimmyshimmer

Workflow or at least some Instructional info.

#6 opened 9 days ago by

leomaxwell973

New activity in unsloth/GLM-4.7-Flash-GGUF 6 days ago

Issue: GLM-4.7-Flash Q6_K - Completely unusable output (looping)

#3 opened 6 days ago by

gannima

New activity in unsloth/LTX-2-GGUF 16 days ago

Your quants are incredible.

🚀 ❤️ 1

#2 opened 16 days ago by

realrebelai

New activity in unsloth/Qwen-Image-Edit-2511-GGUF 29 days ago

Dec 26: Updated to work for stablediffusion.cpp. And apply index_timestep_zero metadata for ComfyUI

👍 8

#6 opened about 1 month ago by

danielhanchen

New activity in unsloth/GLM-4.7-GGUF 29 days ago

UD-Q4_K_XL Error when UD-Q3_K_XL Works.

#1 opened about 1 month ago by

mtcl

New activity in unsloth/Qwen-Image-Edit-2511-GGUF about 1 month ago

__index_timestep_zero__ in metadata?

#4 opened about 1 month ago by

willhsmit

New activity in unsloth/GLM-4.7-GGUF about 1 month ago

UD-Q5_K_XL seemingly broken

#2 opened about 1 month ago by

Nimbz

New activity in unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF about 1 month ago

Pretty bad results compared to Devstral 1 (?)

#3 opened about 2 months ago by

bonswouar

Fixed system prompt + Updates

👍 5

#5 opened about 2 months ago by

danielhanchen

New activity in unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF about 2 months ago

Jan 12 2026: Qwen3-Next updated with iMatrix + Improved performance!

👍 3

#3 opened about 2 months ago by

danielhanchen

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

BF16 or Q8_K_XL - which would give more accurate coding results?

#6 opened about 2 months ago by

TimothyRoo

New activity in unsloth/Ministral-3-14B-Instruct-2512-GGUF about 2 months ago

Examples of how to include an image in the input using a URL and using base64.

#2 opened about 2 months ago by

Oyounghyun

mmproj files?

👍 2

#1 opened about 2 months ago by

blankreg

New activity in unsloth/ERNIE-4.5-21B-A3B-PT-GGUF 2 months ago

update the gguf

#4 opened 3 months ago by

engrtipusultan

Michael Han

AI & ML interests

Recent Activity

Organizations

shimmyshimmer's activity

Infinite thinking (after </thinking> tag with updated quants

Ollama Support

High CPU Usage / Slow Context Processing

Jan 21: GGUFs all UPDATED!!!

Kind of broken.

New Sample Workflow!!

Workflow or at least some Instructional info.

Issue: GLM-4.7-Flash Q6_K - Completely unusable output (looping)

Your quants are incredible.

Dec 26: Updated to work for stablediffusion.cpp. And apply index_timestep_zero metadata for ComfyUI

UD-Q4_K_XL Error when UD-Q3_K_XL Works.

__index_timestep_zero__ in metadata?

UD-Q5_K_XL seemingly broken

Pretty bad results compared to Devstral 1 (?)

Fixed system prompt + Updates

Jan 12 2026: Qwen3-Next updated with iMatrix + Improved performance!

BF16 or Q8_K_XL - which would give more accurate coding results?

Examples of how to include an image in the input using a URL and using base64.

mmproj files?

update the gguf