shisa-ai/Qwen3.8-27B-Q4_K_M-DMS-W8192
Updated
lhl PRO
leonardlin
AI & ML interests
None yet
Recent Activity
updated a model 2 days ago
shisa-ai/Qwen3.8-27B-Q4_K_M-DMS-W8192 published a model 2 days ago
shisa-ai/Qwen3.8-27B-Q4_K_M-DMS-W8192 liked a model 3 days ago
pyros-vault/Ornith-1.5-35B-A3B-oQ6e-fixed-mtpOrganizations
updated a
model 2 days ago
published a
model 2 days ago
liked 4
models 3 days ago
pyros-vault/Ornith-1.5-35B-A3B-oQ6e-fixed-mtp
Image-Text-to-Text • 8B • Updated • 249 • 1
RukaRat/Ornith-1.5-35B-A3B-oQ6-gs128-mtp-vision
Image-Text-to-Text • 8B • Updated • 218 • 1
jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
Text Generation • 27B • Updated • 2.26k • 43
gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090
Image-Text-to-Text • 15B • Updated • 145k • 124
No speculative decoding, No QAT
8
#21 opened 4 days ago
by 
engrtipusultan
Qwen 3.8 27b wins?
👍 2
3
#14 opened 5 days ago
by 
Tdamre
mtp.* tensors look like random init, not trained weights
🧠👍 8
14
#10 opened 6 days ago
by 
EryriLabs
posted an update 6 days ago
Post
104
I've trained an uploaded a proper MTP head for Ornith 1.5:
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8
updated 2
models 6 days ago
published 2
models 6 days ago
updated a
model 6 days ago
published a
model 6 days ago
liked 2
models 7 days ago
liked a
model 8 days ago
