Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Joysulem
/
FireEcho
like
0
Text Generation
Qwen/Qwen3-Omni-30B-A3B-Instruct
fireecho
qwen3-omni
inference
triton
quantization
Mixture of Experts
fp4
fp8
int2
single-gpu
blackwell
hebbian
speculative-decoding
custom-kernel
Eval Results (legacy)
4-bit precision
custom_fp4
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
main
FireEcho
/
READ ME FILES
296 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
Joysulem
Upload 3258 files
b5bff9c
verified
2 months ago
Plans important Documents
Upload 3258 files
2 months ago
AQLM 2-bit — What We'd Need.md
5.89 kB
Upload 3258 files
2 months ago
Bible Kernel Path command.md
4.14 kB
Upload 3258 files
2 months ago
FE-MX: Age-Adaptive Microscaling for Hebbian Memory .md
20.9 kB
Upload 3258 files
2 months ago
FE-MX: FireEcho Age-Adaptive Microscaling for Hebbian Memory.md
39.6 kB
Upload 3258 files
2 months ago
FE-XC — FireEcho Xtreme Compress (Codebook 2-Bit Quantization).md
10.8 kB
Upload 3258 files
2 months ago
FE-XT.md
49.8 kB
Upload 3258 files
2 months ago
FireEcho — Persistent AGI Memory System.md
40.4 kB
Upload 3258 files
2 months ago
HF blog post.txt
8.26 kB
Upload 3258 files
2 months ago
Model Card.md
11.6 kB
Upload 3258 files
2 months ago
NEXT_SESSION_INSTRUCTIONS.md
6.18 kB
Upload 3258 files
2 months ago
README.md
5.5 kB
Upload 3258 files
2 months ago
The Key Insight We Were Missing.md
10.8 kB
Upload 3258 files
2 months ago
