phak
phakio
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
AesSedai/Mistral-Small-4-119B-2603-GGUF liked a model 7 days ago
Tesslate/OmniCoder-9B-GGUF new activity 8 days ago
AesSedai/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF:This model is a gem for agentic work flows.Organizations
None yet
This model is a gem for agentic work flows.
๐ 1
1
#1 opened 8 days ago
by
phakio
Such a great model. (RTX 4090 Performance data inside)
๐ฅ 1
3
#4 opened 12 days ago
by
phakio
How to Run GLM-5 Locally Guide! ๐ฅ
๐ฅ 2
4
#4 opened about 1 month ago
by
danielhanchen
Performance on Intel QYFS, 512GB DDR5 and 96GB VRAM
๐ 1
1
#3 opened about 1 month ago
by
phakio
4x24GB VRAM Spread Results.
๐ 3
23
#2 opened 3 months ago
by
phakio
Definitely interested in this one!
๐ 2
25
#1 opened 4 months ago
by
mtcl
Testing smol-IQ4_KSS
๐ 1
9
#8 opened 4 months ago
by
shewin
testing smol-IQ4-KSS
๐๐ 3
5
#7 opened 5 months ago
by
shewin
(IQ2_XSS) Initial Performance Results Inside ใ96GB VRAM / 256GB DDR5 ใ
๐๐ฅ 2
3
#3 opened 5 months ago
by
phakio
Performance on Gaming Rig
โค๏ธ๐ 1
9
#5 opened 6 months ago
by
ubergarm
The duality of a budget system...
๐ 1
16
#3 opened 6 months ago
by
phakio
CPU only build is getting ~21t/s!
๐ง ๐ฅ 2
1
#2 opened 6 months ago
by
phakio
IQ3_K Results inside!
๐โค๏ธ 2
15
#3 opened 6 months ago
by
phakio
Good outputs! Even at 2.0bpw!
๐ 2
14
#1 opened 6 months ago
by
phakio
Error when running in VLLM
๐ 2
21
#1 opened 6 months ago
by
d8rt8v
Decent performance with 96GB VRAM / 256GB DDR5
โค๏ธ 3
1
#1 opened 6 months ago
by
phakio
Neglible loss of PPL when using only 6 of 8 experts
๐ฅ 2
3
#7 opened 7 months ago
by
whoisjeremylam
quant req: 256 GB RAM + 96 GB VRAM
๐ 1
28
#1 opened 7 months ago
by
whoisjeremylam
IQ2_KL Testing - Runs Great Until The Model The Model The Model (lol)
๐ฅ 1
8
#4 opened 7 months ago
by
phakio