peonist-ai/halogen-qwen3.8-flash-next
Text Generation • Updated • 138
N
peonist
AI & ML interests
None yet
Recent Activity
new activity about 6 hours ago
crucible-labs/Qwen3.6-35B-A3B-REAP-48-v2-GGUF:Model keeps assuming key points are a typo updated a model 1 day ago
peonist-ai/halogen-qwen3.8-flash-next new activity 6 days ago
peonist-ai/halogen-qwen3.8-flash-next:Ablated model?Organizations
Model keeps assuming key points are a typo
1
#2 opened about 7 hours ago
by 
Algiefonso
updated a
model 1 day ago
Ablated model?
40
#4 opened 18 days ago
by 
haign
liked a
model 7 days ago
Q5 or Q6 quants ?
7
#6 opened 14 days ago
by 
auf1r2
Variable MTP and ngram
1
#9 opened 7 days ago
by 
davenetdev
Very fast.
25
#1 opened 23 days ago
by 
theTross
What an absolute godlike tool. The speed is insane!
❤️ 10
22
#7 opened 12 days ago
by 
DarkCobalt
Can the model size be further reduced to lower initial loading overhead
4
#8 opened 9 days ago
by 
yhx03
liked a
model 12 days ago
updated a
model 13 days ago
Donato's video on halogen & qwen3.8 flash
👍❤️ 8
2
#5 opened 16 days ago
by 
iamtc
How about a 3-bit quant?
8
#3 opened 19 days ago
by 
PhilTomson
Engram SSD Offloading
4
#2 opened 22 days ago
by 
justanonymuser
Ablated model?
40
#4 opened 18 days ago
by haign
How about a 3-bit quant?
8
#3 opened 19 days ago
by PhilTomson
updated a
model 19 days ago
Engram SSD Offloading
4
#2 opened 22 days ago
by justanonymuser
Very fast.
25
#1 opened 23 days ago
by theTross
Very Good Quant
3
#1 opened 24 days ago
by 
DarkKitsune