owao
owao
AI & ML interests
None yet
Recent Activity
new activity about 13 hours ago
bottlecapai/ThinkingCap-Qwen3.8-27B-GGUF:quantization method liked a model about 14 hours ago
ibm-granite/granite-speech-5.0-470m-turboctc-nc liked a model about 17 hours ago
bottlecapai/ThinkingCap-Qwen3.8-27B-GGUFOrganizations
quantization method
3
#3 opened about 18 hours ago
by
owao
"The generation cap is 253,952 tokens for most benchmarks."
1
#3 opened about 18 hours ago
by
owao
New Model based on Qwen 3.8
➕🔥 27
18
#23 opened about 2 months ago
by
jaskfsafdjlk
Congrats
🔥 1
9
#2 opened 11 days ago
by
owao
This model is HORRIBLE for coding. don't waste your time.
🧠👍 14
10
#22 opened 6 days ago
by
avicohen
I wanted a drawing and it actually gave a fuck 😂
4
#2 opened 11 days ago
by
owao
my brain is broken
❤️ 1
4
#2 opened 13 days ago
by
NILKNARFGonzo
Q4_K_M slower than Q8_0
3
#4 opened 14 days ago
by
nerun
Thanks!
👍❤️ 4
1
#1 opened 18 days ago
by
AxionLab-official
[bot] Conversion to Parquet
#1 opened about 1 month ago
by
parquet-converter
New Refresh with added Tool Calling in calibration dataset and improved imatrix
❤️ 9
13
#21 opened 8 months ago
by
danielhanchen
Mixed up model names
2
#1 opened 26 days ago
by
owao
Are these quants using Unsloth UD 3.0 or 2.0?
5
#20 opened 29 days ago
by
InfernalDread
5090 Qwen3.8-27B NVFP4 Best setup for real world use (vLLM wins over llama)
17
#132 opened about 1 month ago
by
marco9899
Super cool!
❤️ 1
7
#2 opened about 1 month ago
by
owao
NVFP4 GGUF Ornith-1.5-35B-A3B ?
2
#7 opened about 1 month ago
by
lanman1
Now we have independent numbers
5
#129 opened about 1 month ago
by
owao
We need to talk about the aliyuncs.com symptom
1
#62 opened about 1 month ago
by
owao
configration for your setup
7
#2 opened about 1 month ago
by
Rahul-fix
Reverse this string: '.DefaultCellStyle'
🔥 3
21
#50 opened about 1 month ago
by
owao