Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen2.5-3B-BonfyreFPQ-v12 – AI Model by NICKO | AlphaNeural AI
You can deploy this model and start earning money today!
NICKO
/
Qwen2.5-3B-BonfyreFPQ-v12
like
0
bonfyre-fpq
v12
rans-entropy
e8-lattice
quantization
Qwen/Qwen2.5-3B
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen 2.5 3B — BonfyreFPQ v12 Native
Format
: .fpq v12 (rANS entropy coded E8 + 6-bit tiles + FP16 scales)
Base model
: Qwen/Qwen2.5-3B (3.09B params)
Size
: 3.1 GB (vs 6.17 GB BF16 = 1.9× compression)
Bits per weight
: 8.43 bpw
Quality
: avg cosine 0.999714, worst 0.998316
Inference validated
: logit cosine 0.9896, top-1 agreement 100% (Qwen2.5-3B)
Wan 2.1 video generation
: successfully generated video from decoded v12 weights
Decode
./bonfyre-fpqx decode model-00001-of-00002.fpq # outputs BF16 safetensors
