FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Paper • 2608.16157 • Published • 73
Michael Fielding PRO
mfielding92
AI & ML interests
Music Mixing and Mastering, Audio Generation, Image and Video Diffusion, LLMs
Recent Activity
upvoted a paper about 22 hours ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution liked a model about 22 hours ago
unsloth/Inkling-Small-GGUF updated a model 8 days ago
mfielding92/thefriend-31b-v2-GGUFOrganizations
None yet
upvoted a paper about 22 hours ago
liked a
model about 22 hours ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
collection 9 days ago
upvoted a paper 9 days ago
commented a
paper 9 days ago
liked a
model 17 days ago
reacted to danielhanchen's post with 👍 17 days ago
Post
2261
We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. 🤯
We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...
1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.
GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth
We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...
1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.
GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth
- 1 reply
liked 2
models 21 days ago
updated a
model 27 days ago
published a
model 27 days ago
updated a
model 27 days ago
published a
model 27 days ago
liked a
model about 1 month ago
