Thanks friend, does that mean there will be reasoning an non reasoning versions?
JM
akierum
·
AI & ML interests
None yet
Recent Activity
new activity 11 days ago
Nanbeige/Nanbeige4.3-33B:KV Optimizations?Organizations
None yet
New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 10 days ago
New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 11 days ago
KV Optimizations?
👍👀 4
11
#8 opened 18 days ago
by 
bobbytaylor
After 6hrs on 3x 3090 it failed with same error many times, no usable code 130K wasted
#29 opened 16 days ago
by akierum
Why no higher quants for those that can't run BF16 ?
4
#8 opened 17 days ago
by akierum
Nanbeige 4.3 33B - HAS NO VISION - How are you suppose to use this for WEB DEV?
👍 2
3
#21 opened 17 days ago
by akierum
Why no quants for Q6 - Q8 - Q8-XL
#12 opened 17 days ago
by akierum
Intel Arc B70 results: 32 T/s with UD-Q6_K, SYCL, MTP
👍 2
6
#114 opened 3 months ago
by 
Testererer
Works great :)
2
#1 opened 29 days ago
by 
sabayon
Q8-XL version same bug as Unsloth - general.file_type Q4_K_M
#20 opened 27 days ago
by akierum
Please release XL quant
3
#5 opened about 1 month ago
by akierum
GGUF versions available via Torrent
2
#123 opened 2 months ago
by 
baiomys
Introducing Unsloth Dynamic v3 Qwen3.8
👍🔥 56
40
#74 opened 3 months ago
by 
danielhanchen
Please add Q8-XL version to make replacement for Unsloth Xl version.
#6 opened about 2 months ago
by akierum
Run 170 tokens/s Qwen3.8-Flash with MTP! ⚡
🔥❤️ 15
25
#56 opened 2 months ago
by danielhanchen
Your model is best in class.
Waiting for Qwen 3.8 27B pi thinking model too.
Your models are the only ones passing that codeneedle test no making empty space errors on first row.
I would suggest releasing the XL versions too as BF16 is out of reach for everyone, and keep up the good work.