Downloads · 30 days
22
11% of all-time downloads
Wan2.1-T2V-14B-BonfyreFPQ3
NICKO/Wan2.1-T2V-14B-BonfyreFPQ3
Wan2.1-T2V-14B-BonfyreFPQ3 is a machine learning model from NICKO. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as apache-2.0.
BonfyreFPQ — BF16 safetensors format. Drop-in replacement, no special loader required.
All-time downloads
205
Public
Parameters
14.3B
28.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors28.6 GB · 100%
At a glance
- Library
- diffusers
- License
- apache-2.0
- Model type
- t2v
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026
- SHA
- d7c4617d
Model card
From the Hugging Face model README
Wan2.1-T2V-14B-BonfyreFPQ3
BonfyreFPQ — BF16 safetensors format. Drop-in replacement, no special loader required.
Usage
Standard BF16 safetensors — load directly in PyTorch, diffusers, or any HuggingFace-compatible framework:
from safetensors.torch import load_file
weights = load_file("model.safetensors")
Or load with the transformers library as usual.
Compression Method
BonfyreFPQ v9/v10 with Bonfyre Weight Algebra:
- Decompose W = L + R (truncated SVD)
- Prune R with hybrid structure-aware pruning
- Curl + divergence energy correction
- FPQ v9 multi-scale encode (LR + E8 + RVQ + QJL + Ghost)
- Decode back to BF16 safetensors
Quality
Per-weight cosine similarity ~0.9999 at ~4 bits/weight. See verified benchmarks.
Compressing Your Own Models
git clone https://github.com/Nickgonzales76017/bonfyre-oss.git && cd bonfyre-oss/cmd/BonfyreFPQ && make
./bonfyre-fpq algebra-compress input.safetensors output.safetensors --bits 3
Links
- Library
- diffusers
- Type
- t2v
- License
- apache-2.0
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026