My AI startup that's all about the `mesh` architecture: a novel solution to the problems of MoE
aquiffoo
aquiffoo
AI & ML interests
small but capable open models.
Recent Activity
updated
a model
8 minutes ago
mesh-labs/v0.1-2x2-stage002
updated
a Space
about 2 hours ago
mesh-labs/README
reacted
to
danielhanchen's
post
with 🔥
about 6 hours ago
Run DeepSeek-V3.1 locally on 170GB RAM with Dynamic 1-bit GGUFs!🐋
GGUFs: https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF
The 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers.
The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends.
Guide: https://docs.unsloth.ai/basics/deepseek-v3.1
Organizations
models
13
aquiffoo/aquif-3-mini
Text Generation
•
3B
•
Updated
•
32
•
1
aquiffoo/aquif-3-moe-17b-a2.8b-thinking
Text Generation
•
17B
•
Updated
•
24
•
1
aquiffoo/aquif-3-moe-17b-a2.8b
Text Generation
•
17B
•
Updated
•
17
aquiffoo/aquif-3-moe-17b-a2.8b-GGUF
Text Generation
•
17B
•
Updated
•
10
aquiffoo/aquif-3-micro
Text Generation
•
0.4B
•
Updated
•
53
•
1
aquiffoo/aquif-3-micro-GGUF
Text Generation
•
0.4B
•
Updated
•
14
aquiffoo/aquif-3-moe-p1-6.7b-a1b
Text Generation
•
7B
•
Updated
•
25
aquiffoo/VLM-MoE-3x124M
0.4B
•
Updated
•
4
aquiffoo/aquif-neo-2-345m-c2
Text Generation
•
0.4B
•
Updated
•
16
aquiffoo/aquif-neo-2-345m-c1
Text Generation
•
0.4B
•
Updated
•
10