A.X K2
Collection
8 items • Updated • 7
oh
hyunw55
AI & ML interests
None yet
Recent Activity
new activity 6 days ago
skt/A.X-K2-ALM:Estimated timeline for model weights release? upvoted a collection 29 days ago
A.X K2Organizations
None yet
Estimated timeline for model weights release?
👍 1
#1 opened 6 days ago
by hyunw55
upvoted a collection 29 days ago
Any plans for a calibration-based AWQ build for better long-context stability?
2
#6 opened 4 months ago
by hyunw55
reacted to DedeProGames's post with 🔥 4 months ago
Post
8594
GRaPE 2 Pro is now available.
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
<thinking_mode> tag. This gives you real control over how hard the model thinks, from skipping the reasoning phase entirely with minimal, all the way up to xtra-Hi for deep, extended thought on hard problems. For most agentic use, auto or low is the move to keep things snappy.It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
contact@skinnertopia.com 
- 1 reply
First Download!
👍 1
5
#1 opened 4 months ago
by 
mtecnic
Hello, thanks for releasing a great model.
👍 1
1
#1 opened 5 months ago
by hyunw55
Thanks for the quick upload
#1 opened 5 months ago
by hyunw55
This quantization model is amzing
❤️👍 2
5
#1 opened 6 months ago
by hyunw55
liked a
model 6 months ago
liked a
model 7 months ago
AWQ quantization please
#2 opened 8 months ago
by hyunw55
Plan for AWQ?
#4 opened 9 months ago
by hyunw55
Possibilities of QAT model versions?
👍 3
1
#1 opened 10 months ago
by 
Tridefender
liked a
model 11 months ago
Plan for AWQ?
➕ 28
3
#8 opened 12 months ago
by hyunw55
liked a
model about 1 year ago
Fails with Unknown CUDA arch error on Dual RTX 3090 with official vLLM image
3
#7 opened about 1 year ago
by hyunw55
AWQ Quantization plz.
👍 1
#9 opened about 1 year ago
by hyunw55
Game-changer for 4x24GB setups! AWQ request
👍 3
3
#1 opened about 1 year ago
by hyunw55
Please, share the custom vLLM source you made
👀 1
#11 opened over 1 year ago
by hyunw55