Instructions to use SUSSYEATING/BAGEL-7B-MoT-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use SUSSYEATING/BAGEL-7B-MoT-ConvRot with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
BAGEL-7B-MoT ConvRot (INT8, INT6, INT4 & INT2 QAT) for ComfyUI
Quantized single-file checkpoints of ByteDance-Seed/BAGEL-7B-MoT in four clean bit widths: Full INT8, Full INT6 (w6a8_int8), Full INT4 (asym_w4a8_int8 + Lloyd-Max codebook), and Full INT2 (w2a8_int8 QAT).
All tiers use ConvRot (block Hadamard rotation) across all 392 coupled MoT Qwen2 + diffusion generation linears, while preserving SigLIP vision encoder, connectors, VAE heads, and embeddings in BF16.
- Full INT8: ConvRot + Act-Order GPTQ.
- Full INT6 (
w6a8_int8) & Full INT4 (asym_w4a8_int8): Split-MoT SmoothQuant + ConvRot + GPTQ Hessian compensation (INT6adds damped coordinate descent;INT4adds sequentialH_qqGPTQ, 2-pass Lloyd-Max refinement, and CUDA damped coordinate descent). - Full INT2 (
w2a8_int8QAT, WIP β Not Final Version): Current work-in-progress two-phase Block-AP + Split-MoT End-to-End Flow-Matching QAT checkpoint (7.20 GB,-75.3%vs BF16) with grouped FP8 scales (gs=16), ConvRot-256 dynamic INT8 activations, and 4-entry symmetric Lloyd-Max codebooks. Preserves fluent<think>reasoning, VLM understanding, and image editing (16.95 dBPSNR /0.89627cos), while text-to-image fidelity is still being actively improved and this is not the final version.
Includes the updated ComfyUI-BAGEL custom node (ComfyUI-BAGEL/ and ComfyUI-BAGEL-93811c5c5931.tar.gz) with native w6a8_int8, asym_w4a8_int8, and w2a8_int8 loader support.
Available Checkpoints
| Precision Tier | File (ComfyUI/models/bagel/) |
Size (vs 29.21 GB BF16) | Quantized MoT Linears |
|---|---|---|---|
| Full INT8 ConvRot | bagel-7b-mot-int8-convrot.safetensors |
16.18 GB (-44.6%) | 392 / 392 MoT INT8 (Act-Order GPTQ) |
| Full INT6 ConvRot | bagel-7b-mot-int6-convrot.safetensors |
13.73 GB (-53.0%) | 392 / 392 MoT INT6 (w6a8_int8 Split-MoT SmoothQuant + CD) |
| Full INT4 ConvRot | bagel-7b-mot-int4-convrot.safetensors |
10.47 GB (-64.2%) | 392 / 392 MoT INT4 (asym_w4a8_int8 Split-MoT SmoothQuant + Sequential GPTQ + CUDA CD) |
| Full INT2 ConvRot QAT (WIP) | bagel-7b-mot-int2-convrot.safetensors |
7.20 GB (-75.3%) | 392 / 392 MoT INT2 (w2a8_int8 Block-AP + Split-MoT E2E QAT) |
All files load directly via ComfyUI-BAGEL using native comfy-kitchen & Triton kernels (ComfyUI >= v0.45.0).
Visual Comparisons (1024x1024, 50 steps, cfg_text_scale=4.0, timestep_shift=3.0)
Text-to-Image
Text-to-Image with <think> Chain-of-Thought
Image Editing (Using Matched BF16 Input Image)
Evaluation Metrics (G4 GPU, ComfyUI v0.45.3)
Measured via scripts/eval_bagel_g4.py directly against unquantized BF16 (bagel-7b-mot.safetensors):
| Precision Tier | Peak VRAM (T2I / Edit) | t2i_cabin_s42 (Time / Cos / SSIM / PSNR) |
t2i_watch_s1337 (Time / Cos / SSIM / PSNR) |
t2i_think_s42 (Time / Cos / SSIM / PSNR) |
edit_cabin_winter_s42 (Time / Cos / SSIM / PSNR) |
understand_cabin |
Report |
|---|---|---|---|---|---|---|---|
| BF16 Baseline | 30.30 / 31.32 GB | 36.60s / ref | 31.58s / ref | 34.72s / ref | 40.48s / ref | 1.59s | g4_bagel_bf16_stats.json |
| Full INT8 ConvRot | 17.17 / 18.19 GB | 28.53s / 0.99687 / 0.96509 / 32.21 dB | 25.96s / 0.99041 / 0.95838 / 26.71 dB | 29.93s / 0.86022 / 0.65112 / 15.18 dB | 33.97s / 0.99611 / 0.95728 / 32.38 dB | 1.96s | g4_bagel_int8_stats.json |
| Full INT6 ConvRot | 14.74 / 15.76 GB | 29.35s / 0.99627 / 0.96011 / 31.38 dB | 27.20s / 0.97862 / 0.91515 / 23.32 dB | 30.86s / 0.94435 / 0.80724 / 19.53 dB | 35.56s / 0.99584 / 0.95983 / 32.46 dB | 1.73s | g4_bagel_int6_stats.json |
| Full INT4 ConvRot | 11.47 / 12.48 GB | 28.71s / 0.98822 / 0.92394 / 28.02 dB | 26.78s / 0.95403 / 0.84440 / 20.30 dB | 35.53s / 0.71399 / 0.56152 / 12.12 dB | 35.08s / 0.99254 / 0.94893 / 28.92 dB | 1.71s | g4_bagel_int4_stats.json |
| Full INT2 ConvRot QAT (WIP) | 8.24 / 9.25 GB | 29.42s / 0.39500 / 0.29581 / 9.32 dB | 27.69s / 0.58873 / 0.31820 / 9.96 dB | 34.71s / 0.37770 / 0.39292 / 7.95 dB | 36.00s / 0.89627 / 0.66833 / 16.95 dB | 1.13s | g4_bagel_int2_stats.json |
ComfyUI Setup & Usage
- Install the updated
ComfyUI-BAGELcustom node: ExtractComfyUI-BAGEL-93811c5c5931.tar.gz(or copyComfyUI-BAGEL/) intoComfyUI/custom_nodes/ComfyUI-BAGEL/. - Download INT8, INT6, INT4, or INT2
.safetensorsintoComfyUI/models/bagel/. - Ensure BAGEL's VAE (
ae.safetensors) is placed inComfyUI/models/vae/. - Hardware note: Requires an Ampere / Ada / Hopper / Blackwell CUDA GPU with
ComfyUI >= v0.45.0andcomfy-kitchen.
License & Attribution
Licensed under Apache License 2.0, matching the upstream ByteDance-Seed/BAGEL-7B-MoT repository and ComfyUI-BAGEL. See NOTICE for full upstream attribution and a summary of modifications made to the weights and custom node.
- Downloads last month
- 126



