Peter Kotsch
LinkuStarto
Β·
AI & ML interests
None yet
Recent Activity
new activity about 10 hours ago
ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:My Experience with the IQ3_S Weight: Fast, Stable, and Instruction-Faithful liked a model 2 days ago
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF liked a model 6 days ago
Qwen/Qwen3.8-27BOrganizations
None yet
My Experience with the IQ3_S Weight: Fast, Stable, and Instruction-Faithful
3
#9 opened about 13 hours ago
by
QilinWan
9B variants?
1
#7 opened 11 days ago
by
LinkuStarto
A crazy thinking model
ππ 14
23
#97 opened about 2 months ago
by
xuguowong
Mtp quality? π€
5
#7 opened about 2 months ago
by
LinkuStarto
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF about 2 months ago
WINNER , Qwen 3.8 27B version(s) // new versions plus GAIN and COLD FUSION training method (and models).
π₯β€οΈ 25
11
#91 opened about 2 months ago
by
DavidAU
Qwen 3.8-27b context usage is about 10x of 3.6-27b
π 4
8
#45 opened about 2 months ago
by
WhiteDan64
DFlash draft model instead of MTP one
π 2
9
#54 opened about 2 months ago
by
artden111
Qwen 3.8 27B
β 2
#5 opened about 2 months ago
by
LinkuStarto
wow
π₯ 18
13
#1 opened about 2 months ago
by
rob-x-ai
First! :)
ππ₯ 9
2
#1 opened about 2 months ago
by
mtecnic
I'm really pleased π
π₯ 1
2
#4 opened about 2 months ago
by
LinkuStarto
No DFlash?
3
#2 opened about 2 months ago
by
crusaderky
thinking level
π 1
1
#12 opened about 2 months ago
by
LinkuStarto
how to partially fix t/s speed generation and partially unlock Dspark full speed capabilities
2
#40 opened 3 months ago
by
LinkuStarto
Unable to get D-Spark Q4_1 working with Q2_0 Model file
9
#11 opened 3 months ago
by
AceTheUnfazed
blk.0.attn_v.weight is missing
1
#1 opened 3 months ago
by
LinkuStarto
Better than expected!
ππ€― 2
2
#1 opened almost 3 years ago
by
appvoid