gghf PRO
gghfez
AI & ML interests
rep-eng
Recent Activity
liked a model about 21 hours ago
teamblobfish/DeepSeek-V4-Flash-GGUF liked a model 1 day ago
DevQuasar/CohereLabs.command-a-plus-05-2026-bf16-GGUF new activity 1 day ago
ubergarm/Kimi-K2.6-GGUF:MTP SupportOrganizations
MTP Support
π 2
9
#13 opened 6 days ago
by
anikifoss
βThe doom lies in yourself, not in your name.β
π 7
479
#15 opened 8 months ago
by
jukofyork
Thank you for releasing the LoRA
β€οΈ 1
1
#1 opened 10 days ago
by
gghfez
How to use MTP in GGUF?
20
#2 opened 23 days ago
by
Friedland
Great model for single GPU use cases.
π₯ 4
16
#1 opened 28 days ago
by
phakio
Much faster IQ2_KS quantization PPL results?
3
#10 opened 30 days ago
by
gghfez
How to disable thinking?
4
#9 opened 30 days ago
by
Hansi2024
How to split this model between 2 (3) GPUs and CPU/RAM ?
30
#12 opened 2 months ago
by
mancub
The Best Kimi Quant!
π₯ 4
13
#1 opened about 1 month ago
by
anikifoss
No think tags.
10
#4 opened about 1 month ago
by
DrRos
Did gemma generated svg?
1
#1 opened about 1 month ago
by
rahul7star
If you have actually used Claude, this dataset is very unlikely to come from Sonnet 4.6
14
#2 opened about 2 months ago
by
CarolineTaylor
IQ5/IQ6 Quants?
π 1
6
#4 opened 3 months ago
by
binahz
Appreciation for IQ1_KT
π₯ 1
7
#5 opened 3 months ago
by
Radamanthys11
βThe doom lies in yourself, not in your name.β
π 7
479
#15 opened 8 months ago
by
jukofyork
Claude 4.6 Opus is released, why you didn't make a dataset?
19
#5 opened 3 months ago
by
MihaiPopa-1
performance of quantized models
3
#61 opened 4 months ago
by
darvec
moonshotai/Kimi-K2.5
π₯ 3
3
#16 opened 4 months ago
by
gghfez