585 26 323

Michael Han

shimmyshimmer

https://unsloth.ai

AI & ML interests

None yet

Recent Activity

updated a collection about 6 hours ago

Unsloth Dynamic 2.0 Quants

reacted to danielhanchen's post with 🤗 about 6 hours ago

Mistral's new SOTA coding models Devstral 2 can now be Run locally! (25GB RAM) 🐱 We fixed the chat template, so performance should be much better now! 24B: https://huggingface.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF 123B: https://huggingface.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF 🧡Step-by-step Guide: https://docs.unsloth.ai/models/devstral-2

reacted to danielhanchen's post with 🚀 about 6 hours ago

View all activity

Organizations

New activity in unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF about 20 hours ago

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

#6 opened about 22 hours ago by

TimothyRoo

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

Pretty bad results compared to Devstral 1 (?)

#3 opened 1 day ago by

bonswouar

New activity in unsloth/Ministral-3-14B-Instruct-2512-GGUF 7 days ago

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

#2 opened 8 days ago by

Oyounghyun

New activity in unsloth/Ministral-3-14B-Instruct-2512-GGUF 9 days ago

mmproj files?

👍 2

#1 opened 9 days ago by

blankreg

New activity in unsloth/ERNIE-4.5-21B-A3B-PT-GGUF 28 days ago

update the gguf

#4 opened about 1 month ago by

engrtipusultan

New activity in unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF about 1 month ago

k6 k xl ud is bugged

👍 1

#2 opened about 1 month ago by

maxpayne07

New activity in unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF about 1 month ago

Q6_K_XL seems corrupted

👍 1

#2 opened about 1 month ago by

AlexPoto

New activity in Qwen/Qwen3-VL-32B-Instruct about 1 month ago

GGUFs have buggy Japanese OCR performance

#4 opened about 1 month ago by

TPH441

New activity in unsloth/Ling-1T-GGUF about 2 months ago

Q8_0 and UD-Q8_K_XL missing parts?

#1 opened about 2 months ago by

superciliousdude

New activity in ibm-granite/granite-4.0-h-small 2 months ago

Is it possible, to fine tune this model on rtx pro 6000?

#2 opened 2 months ago by

win10

New activity in unsloth/gpt-oss-20b-GGUF 2 months ago

TEMPLATE for Ollama Modelfile?

#29 opened 3 months ago by

Ray9821

Delete config.json

#33 opened 2 months ago by

TarunKM

New activity in unsloth/GLM-4.6-GGUF 2 months ago

what's the best Q4 quant?

#4 opened 2 months ago by

SlavikF

New activity in unsloth/granite-4.0-h-small-GGUF 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

New activity in unsloth/granite-4.0-h-tiny-GGUF 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

New activity in unsloth/granite-4.0-h-micro-GGUF 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

New activity in unsloth/granite-4.0-micro-GGUF 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

New activity in unsloth/granite-4.0-micro 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

New activity in unsloth/granite-4.0-h-micro 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

New activity in unsloth/granite-4.0-h-tiny 2 months ago

Update README.md

#1 opened 2 months ago by

shimmyshimmer

Michael Han

AI & ML interests

Recent Activity

Organizations

shimmyshimmer's activity

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

Pretty bad results compared to Devstral 1 (?)

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

mmproj files?

update the gguf

k6 k xl ud is bugged

Q6_K_XL seems corrupted

GGUFs have buggy Japanese OCR performance

Q8_0 and UD-Q8_K_XL missing parts?

Is it possible, to fine tune this model on rtx pro 6000?

TEMPLATE for Ollama Modelfile?

Delete config.json

what's the best Q4 quant?

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md