blakkd
owao
AI & ML interests
None yet
Recent Activity
liked a model 4 days ago
ResembleAI/chatterbox-nano liked a model 9 days ago
mudler/Agents-A1-APEX-GGUF new activity 9 days ago
unsloth/Qwen3.6-27B-MTP-GGUF:--n-gpu-layers or -nglOrganizations
--n-gpu-layers or -ngl
2
#12 opened about 2 months ago
by
owao
Does Ornith-1.0-35B preserve historical reasoning traces like Qwen3.6?
6
#16 opened 12 days ago
by
eflaneble
Awesome model
👍❤️ 15
10
#2 opened 16 days ago
by
pengzhi27
What are use cases for this model?
👍 1
3
#6 opened 15 days ago
by
Duonglv
LMStudio sees the GGUF as MTP enabled
4
#2 opened 21 days ago
by
Hachann
Ear massage
🤯👍 3
#4 opened about 1 month ago
by
owao
Vllm - Out of Memory Error
6
#1 opened 2 months ago
by
H-J-D
Broken Tool Calling?
5
#1 opened about 2 months ago
by
And1mon
Plans for a multi actor version?
3
#3 opened about 2 months ago
by
mindplay
FYI : --spec-type mtp syntax has changed to --spec-type draft-mtp
👍 3
3
#14 opened about 2 months ago
by
qenme
presence-penalty
5
#8 opened about 2 months ago
by
owao
This model is a bulldozer
👍 1
#10 opened about 2 months ago
by
owao
QWEN35_MTP requires nextn_predict_layers > 0.
➕👍 5
14
#2 opened 2 months ago
by
jidaigeist
Great job, impressive!
❤️ 3
#2 opened 2 months ago
by
owao
🚩 Report: Spam
#2 opened 3 months ago
by
owao
Is it really better in real world task?
👀 1
10
#50 opened 3 months ago
by
BornSaint
2-bit Qwen3.6-27B made 26 tool calls! 🔥
🧠🔥 11
4
#15 opened 3 months ago
by
danielhanchen
F5 F5 F5 F5 F5 F5 F5 F5 F5
❤️ 18
9
#2 opened 3 months ago
by
Ukro
Qwen 3.6 is much slower than Qwen 3.5 for the same quatization: UD-Q4_K_XL
10
#8 opened 3 months ago
by
adr-insc
My RTX 3090 ran out of excuses: Qwen3.6-35B-A3B
🔥❤️ 32
7
#37 opened 3 months ago
by
Kukedlc