Hugging Face's logo
Michael Han's picture
329 23 244

Michael Han

shimmyshimmer
reach-vb's profile picture Codingstark's profile picture DeepFount's profile picture
·
https://unsloth.ai

AI & ML interests

None yet

Recent Activity

updated a model about 2 hours ago
unsloth/Qwen3-30B-A3B-128K-GGUF
updated a model about 2 hours ago
unsloth/Qwen3-235B-A22B-128K-GGUF
updated a model about 2 hours ago
unsloth/Qwen3-0.6B-GGUF
View all activity

Organizations

Qwen's profile picture Unsloth AI's profile picture Hugging Face Discord Community's profile picture

shimmyshimmer's activity

New activity in unsloth/Qwen3-235B-A22B-GGUF about 4 hours ago

Amazing, uses humble 255Gb RAM on my ancient 2014 Xeon PC for Q8

1
1
#15 opened about 13 hours ago by
krustik
New activity in unsloth/Qwen3-30B-A3B-GGUF about 7 hours ago

Latest updates?

4
3
#10 opened about 10 hours ago by
Dampfinchen
New activity in unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF about 7 hours ago

Can`t see the image in LM studio.

6
#1 opened about 1 month ago by
Technobiotik
New activity in unsloth/Qwen3-30B-A3B-bnb-4bit about 12 hours ago

unslot-bnb-4bit for Qwen MoE models

5
#2 opened 3 days ago by
S1M0N38
New activity in unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF about 13 hours ago

Vision not working on ollama - Tried updating templates

3
#2 opened 8 days ago by
usamakenway
New activity in unsloth/Qwen3-235B-A22B-GGUF about 20 hours ago

Why are XL quants smaller than M quants?

4
#11 opened 1 day ago by
ChuckMcSneed
New activity in unsloth/Qwen3-0.6B-GGUF about 20 hours ago

Any chance of a 128k version so we can use it as a draft model for the larger 128k models?

3
4
#3 opened 3 days ago by
smcleod
New activity in unsloth/gemma-3-27b-it-unsloth-bnb-4bit about 20 hours ago

significant extra memory usage compared to the other 27b

2
#4 opened 1 day ago by
FlorinAndrei
New activity in unsloth/Qwen3-235B-A22B-GGUF about 20 hours ago

Finetuning possible?

2
#12 opened 1 day ago by
edgeinfinity
New activity in unsloth/GLM-4-32B-0414-GGUF about 20 hours ago

128k version of YARN

2
2
#6 opened 2 days ago by
sovetboga
New activity in unsloth/Qwen3-14B-unsloth-bnb-4bit 1 day ago

Please check if the model file is damaged and cannot chat normally

7
#2 opened 1 day ago by
ShelterW
New activity in unsloth/Qwen3-235B-A22B-GGUF 1 day ago

config.json "max_position_embeddings": 40960,

2
#10 opened 2 days ago by
koushd
New activity in unsloth/Qwen3-235B-A22B-128K-GGUF 1 day ago

There must be something wrong with the size

2
2
#8 opened 2 days ago by
lingyezhixing
New activity in unsloth/GLM-4-32B-0414-GGUF 1 day ago

AMD Issue?

5
#5 opened 3 days ago by
knarp

FIXED: Template bug fixed in llama.cpp

2
6
#4 opened 3 days ago by
sovetboga
New activity in unsloth/Qwen3-30B-A3B-GGUF 2 days ago

`UD-Q4_K_XL` or `Q4_K_M`?

9
#6 opened 3 days ago by
pootow
New activity in unsloth/Qwen3-8B-128K-GGUF 2 days ago

128k are dynamic quants too?

1
#4 opened 2 days ago by
PlatonicSkeptic
New activity in unsloth/Qwen3-30B-A3B-GGUF 2 days ago

Please quantize a Q5_K_S version

1
1
#9 opened 2 days ago by
fakezeta
New activity in unsloth/Qwen3-30B-A3B-128K-GGUF 2 days ago

UD-Q5_K_XL ?

1
#3 opened 2 days ago by
AaronFeng753
New activity in unsloth/Qwen3-30B-A3B-GGUF 2 days ago

Not compatible with transformers library

2
#8 opened 2 days ago by
Xeenxavier007