Anserwise/AWAXIS-Hybrid-28B
Text Generation β’ 28B β’ Updated β’ 75 β’ 2
Jinki Jeong PRO
Anserwise
AI & ML interests
None yet
Recent Activity
upvoted a collection about 20 hours ago
VKAE Accelerated upvoted an article 1 day ago
Adding a GPU Without Building One reacted to SeaWolf-AI's post with π 1 day ago
π Adding a GPU without building one
AI is usually framed as "how smart is the model / how many GPUs did you buy." The real bottleneck is elsewhere β how efficiently you use the GPUs you already have.
Training happens once; inference runs the entire time users use your product. So a service's economics come down to cost per token. Inference acceleration uses software to pull several times more out of the same GPU β the effect of plugging in one more "virtual GPU."
VIDRAFT's VKAE, measured (B200, same-harness, no quality loss):
Qwen3.5-35B-A3B (MoE): 25.7 β 601 tok/s (23.4Γ)
Darwin-36B-Opus (in-house MoE): 25.0 β 280.8 (11.2Γ)
10,000+ tok/s peak aggregate under concurrency
The key: it's reproducible β model + serving shipped as one container.
docker pull vidraft/qwen35-vkae:601
Don't take our word for it β run it yourself. The mechanism will be released as a paper.
π Leaderboard & demo π https://huggingface.co/spaces/VIDraft/vkae
Articles π https://huggingface.co/blog/FINAL-Bench/vkae-leaderboardOrganizations
None yet
Anserwise/AWAXIS-KR-31B
Image-Text-to-Text β’ 52B β’ Updated β’ 98 β’ 4
Anserwise/AWAXIS-Think-31B
Text Generation β’ 31B β’ Updated β’ 68 β’ 2
Anserwise/AWAXIS-Think-28B
Text Generation β’ 28B β’ Updated β’ 31 β’ 17
Anserwise/AWAXIS-Think-27b
Text Generation β’ 27B β’ Updated β’ 5 β’ 1