LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0
Text Generation • 28B • Updated • 200 • 2
AI & ML interests
None defined yet.
Recent Activity
View all activity
Safetensors model request
👍 1
1
#7 opened 16 days ago
by 
SFPLM
kvyb
updated a
model 1 day ago
kvyb
published a
model 1 day ago
kvyb
updated a
model 1 day ago
kvyb
published a
model 1 day ago
kvyb
updated a
model 1 day ago
kvyb
published a
model 1 day ago
kvyb
updated a
model 1 day ago
Lower variants?
8
#1 opened about 1 month ago
by 
JasonGWarrior
Question about tool calling / function calling reliability of this model?
2
#9 opened 11 days ago
by 
vM2k
Its just too random
6
#10 opened 9 days ago
by 
kyoufi
Post
91
Qwen3.8-27B-Humanlike-Chat 2.0 is out.
It still texts like a person with no system prompt. Now it also calls tools, follows instructions, and writes the formal email you asked for, then goes back to texting.
vs the abliterated base it's built on:
- IFBench 37.3 → 43.7
- When2Call 48 → 58
- A blind judge took its reply for the real person's 23.5% of the time (official Qwen3.8-27B: 15.1%)
Trained with on-policy distillation: the model writes its own replies and a teacher grades every token.
GGUF from IQ4_XS to BF16, plus a free API, no key needed.
👉 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF
Try it: LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat
It still texts like a person with no system prompt. Now it also calls tools, follows instructions, and writes the formal email you asked for, then goes back to texting.
vs the abliterated base it's built on:
- IFBench 37.3 → 43.7
- When2Call 48 → 58
- A blind judge took its reply for the real person's 23.5% of the time (official Qwen3.8-27B: 15.1%)
Trained with on-policy distillation: the model writes its own replies and a teacher grades every token.
GGUF from IQ4_XS to BF16, plus a free API, no key needed.
👉 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF
Try it: LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat
- 1 reply
Model request : qwen3.5-9B
2
#8 opened 14 days ago
by 
Exo87
Repetition and topic-looping issue: mitigation live, checkpoint updates next
#6 opened 18 days ago
by 
kvyb
Request to add an IQ4_XS quantization.
👍🚀 1
3
#5 opened 21 days ago
by 
yybl
PLEASE released the dataset for this!
👀👍 4
2
#4 opened 22 days ago
by 
KidRodelo
Any plans to make one with Gemma models ?
👍 4
1
#3 opened 23 days ago
by 
AnonCat
kvyb
updated a
Space 24 days ago
Rambles off into nonsense
👀 2
2
#2 opened 27 days ago
by 
lothinx
kvyb
published a
Space about 1 month ago