Thiago de Arruda Padilha
tarruda
AI & ML interests
None yet
Recent Activity
new activity about 20 hours ago
tarruda/Qwen3.5-397B-A17B-GGUF:Great job on this one! new activity 1 day ago
AesSedai/Qwen3.5-397B-A17B-GGUF:IQ2_XS? updated a model 3 days ago
tarruda/Qwen3.5-397B-A17B-GGUFOrganizations
None yet
Great job on this one!
1
#1 opened about 21 hours ago
by
ubergarm
IQ2_XS?
๐ฅ 2
30
#6 opened 20 days ago
by
tarruda
Impressive work!
๐ 1
1
#1 opened 9 days ago
by
tarruda
Any chance of IQ2_XXS? IQ2_XS is just slightly too big for Strix Halo.
6
#2 opened 11 days ago
by
Cortex0833
imatrix source
3
#1 opened 16 days ago
by
coughmedicine
Re-generate GGUFs to benefit from 10% speedup
2
#22 opened 17 days ago
by
tarruda
imatrix?
1
#5 opened 26 days ago
by
tarruda
Question
1
#1 opened 19 days ago
by
tarruda
Other quants?
9
#1 opened about 1 month ago
by
yamikumods
Qwen3.5 GGUF Evaluation Results
๐ 6
9
#9 opened about 1 month ago
by
danielhanchen
Question about benchmark results
๐ฅ๐ 2
6
#5 opened 30 days ago
by
tarruda
Some benchmarks for IQ4_XS
๐ฅ 4
5
#3 opened 30 days ago
by
tarruda
q8_0?
โค๏ธ 1
1
#1 opened about 1 month ago
by
tarruda
A couple of questions about one of the recipes
4
#2 opened about 1 month ago
by
tarruda
Quant comparison versus "smol-IQ2_XS"
4
#5 opened about 1 month ago
by
coder543
Some lm-evaluation-harness results for smol-IQ2_XS
โค๏ธ๐ฅ 2
1
#8 opened about 1 month ago
by
tarruda
Some benchmarks
๐ฅ 3
2
#13 opened about 1 month ago
by
tarruda
smol-IQ2_XS is a damn good quant!
๐๐ฅ 7
7
#2 opened about 1 month ago
by
tarruda
Which quant is best for Mac?
4
#6 opened about 2 months ago
by
thejson