Michael Han
shimmyshimmer
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
unsloth/Qwen-Image-2.1-FP8:model_index.json new activity 16 days ago
unsloth/Qwen-Image-2.1-GGUF:Run Qwen-Image-2.1 locally! new activity 18 days ago
unsloth/Qwen-Image-2.1-FP8:Doesn't even work in comfyui lmfaoOrganizations
model_index.json
π 2
3
#2 opened 17 days ago
by 
amaranus
Run Qwen-Image-2.1 locally!
9
#4 opened 18 days ago
by 
danielhanchen
Doesn't even work in comfyui lmfao
2
#1 opened 18 days ago
by 
StormTMads
Qwen 3.8 IQ2 XXS - new version Lower perfomances
4
#122 opened about 1 month ago
by 
GrahamShandor
Run 170 tokens/s Qwen3.8-Flash with MTP! β‘
π₯β€οΈ 13
24
#56 opened about 1 month ago
by danielhanchen
Q3 K M (13.8 GB) is larger than UD Q3 K XL(13.4GB)
π 1
3
#58 opened about 2 months ago
by 
whatitall
Quality enhance
#80 opened about 2 months ago
by 
r1yyxn
Why Qwen3.8-27B-UD-Q8_K_XL.gguf is not updated like other quants?
7
#91 opened about 2 months ago
by 
akierum
I tried to improve on UD-Q8_K_XL and succeeded
π₯ 4
2
#103 opened about 2 months ago
by 
KissMyShinyArse
[Obsolete?] "Thinking" loop issue
5
#118 opened about 1 month ago
by 
paq85
more qaunts pls
2
#105 opened about 2 months ago
by 
Duswishdb
Bug: Gibberish output on Strix Halo since Unsloth Desktop sets GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 on HIP build
π 1
10
#30 opened about 1 month ago
by 
adi-0
Apple Silicon: LM Studio can't load it yet, and GGUF gives up the MTP head (measured 3.3x on M4 Max)
#50 opened about 1 month ago
by 
Sinojen
imatrix file
1
#25 opened about 1 month ago
by 
erazortt
Unsloth Studio vs Unsloth Desktop Day Zero Support
4
#8 opened about 2 months ago
by 
Chuck572
Request: Single-file GGUF for Ollama support
π 2
6
#18 opened about 2 months ago
by 
giodasisa
file size (quantization)
2
#16 opened about 2 months ago
by 
jacek2024
Vision
π 1
9
#19 opened about 2 months ago
by 
hgeist
LM Studioθ½ε¦η΄ζ₯ζ―ζοΌ
1
#26 opened about 1 month ago
by 
kelei999999
