Thanks friend, does that mean there will be reasoning an non reasoning versions?
JM
akierum
·
AI & ML interests
None yet
Recent Activity
new activity 13 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:Run 170 tokens/s Qwen3.8-Flash with MTP! ⚡ new activity 14 days ago
unsloth/Qwen3.8-27B-GGUF:Introducing Unsloth Dynamic v3 Qwen3.8Organizations
None yet
Please add Q8-XL version to make replacement for Unsloth Xl version.
#6 opened 3 days ago
by akierum
Run 170 tokens/s Qwen3.8-Flash with MTP! ⚡
🔥❤️ 13
18
#56 opened 19 days ago
by 
danielhanchen
Introducing Unsloth Dynamic v3 Qwen3.8
👍🔥 55
37
#74 opened about 1 month 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.
Where is the normal Q8 version? to fit into 48GB VRAM with 256k context?
5
#13 opened 21 days ago
by akierum
WE NEED 35B A3B
👍🔥 18
3
#3 opened 26 days ago
by 
AsThirtyThree
will there be qwen 3.8 27B version ?
3
#5 opened about 1 month ago
by akierum
the bartowski quantization works fine with mmproj from qwen no need for modifications
#1 opened 27 days ago
by akierum
WOW! Not kidding, this model nuts! 💥
❤️ 9
4
#29 opened about 1 month ago
by 
auf1r2
for 3090 MTP and gguf is best for performance 250k context and accuracy.
1
#8 opened 28 days ago
by akierum
reacted to DavidAU's post with 😎🚀🧠🤝🔥👍 29 days ago
Post
22496
Qwen3.8 - 27B - COLD FUSION
Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output.
Increase in general intelligence too (all 7 critical benches); bench marks posted.
Trained using the COLD FUSION method (GAIN + UNSLOTH).
NOTE: This is NOT a heretic / uncensored version.
MTP and GGUF NEO MAX quants:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF
SOURCE:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output.
Increase in general intelligence too (all 7 critical benches); bench marks posted.
Trained using the COLD FUSION method (GAIN + UNSLOTH).
NOTE: This is NOT a heretic / uncensored version.
MTP and GGUF NEO MAX quants:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF
SOURCE:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
- 7 replies
Recommended Sampling, etc Settings
🧠 1
2
#18 opened about 1 month ago
by 
Shad3
Why Qwen3.8-27B-UD-Q8_K_XL.gguf is not updated like other quants?
7
#91 opened about 1 month ago
by akierum
why Huihui-Qwen3.8-27B-abliterated-Q8_0_L.gguf is bigger than unsloth Q8-XL?
1
#7 opened about 1 month ago
by akierum