ModelListadosExterno

Convrot Models

This repository contains a collection of popular generative models quantized to INT8 using the ConvRot method for optimized inference with minimal quality loss.

Fontehuggingface.co/supermind/int8_convrot_models/tree/eb6682675836a42aa91fd4effcd77d68fe60ff42

TipoOtherModelo baseZ-Image TurboVersãoRevision eb66826Dnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 2,99–30,8 GB
Modelo base: Z-Image Turbo
Versão: vRevision eb66826
Atualizado: 1 de out. de 2026
Downloads: 0
Tarefas: Edição de imagem
Fonte: Hugging Face

Descrição da fonte

📦 INT8 Quantized Model Collection (ConvRot)

This repository contains a collection of popular generative models quantized to INT8 using the ConvRot method for optimized inference with minimal quality loss.

Almost all models were quantized from the original BF16 weights using the quant_int8_convrot.py script with the --mseclip attribute for calibration.

🛠️ Quantization Details

Base Precision: BF16 → INT8 ConvRot
Method: ConvRot (Convolution Rotation)
Calibration: --mseclip for per-layer clipping optimization (couple has --absmax)
Tool: quant_int8_convrot.py (Comfy-Org)

flux-2-dev_int8_convrot_quantops.safetensors was first quantized in ComfyUI using ComfyUI-QuantOps, then convert to int8_convrot format via convert_to_comfy.py

📂 Included Models

Model Name	Original Source	Notes
Checkpoints
`ltx-2.3-22b-dev_int8_convrot.safetensors`	LTX 2.3 22B	—

Diffusion models
`flux-2-dev_int8_convrot_quantops.safetensors`	Flux-2 dev	via ComfyUI-INT8-Fast
`flux-2-dev_int8_convrot_mseclip.safetensors`	Flux-2 dev	—
`flux-2-dev_int8_convrot_absmax.safetensors`	Flux-2 dev	—
`flux-2-klein-4b_int8_convrot.safetensors`	Flux-2 Klein 4B	—
`flux-2-klein-9b_int8_convrot.safetensors`	Flux-2 Klein 9B	—
`flux-2-klein-9b-kv_int8_convrot.safetensors`	Flux-2 Klein 9B KV	—
`qwen_image_2512_int8_convrot.safetensors`	Qwen Image 2512	—
`qwen_image_edit_2511_int8_convrot.safetensors`	Qwen Image Edit 2511	—
`z_image_int8_convrot.safetensors`	Z-Image	—
`z_image_turbo_int8_convrot.safetensors`	Z-Image Turbo	—
`krea2_raw_int8_convrot.safetensors`	Krea 2 Raw	—
`krea2_turbo_int8_convrot.safetensors`	Krea 2 Turbo	—
`ideogram4_int8_convrot.safetensors`	Ideogram 4	via dequant FP8
`ideogram4_unconditional_int8_convrot.safetensors`	Ideogram 4 Uncond.	via dequant FP8

3D models
`trellis_2_int8_convrot.safetensors`	Trellis 2	—
`pixal3d_int8_convrot.safetensors`	Pixal 3D	—

Text encoders
`gemma4_e4b_it_int8_convrot.safetensors`	Gemma 4 E4B IT	—
`gemma_2_2b_it_elm_int8_convrot.safetensors`	Gemma 2 2B IT	—
`qwen3.5_4b_int8_convrot.safetensors`	Qwen 3.5 4B	—
`qwen3vl_8b_int8_convrot.safetensors`	Qwen 3 VL 8B	—
`qwen3vl_4b_int8_convrot.safetensors`	Qwen 3 VL 4B	—
`qwen_3_8b_int8_convrot.safetensors`	Qwen 3 8B	—
`qwen_3_4b_int8_convrot.safetensors`	Qwen 3 4B	—
`qwen_2.5_vl_7b_int8_convrot.safetensors`	Qwen 2.5 VL 7B	—
`mistral_3_small_flux2_int8_convrot.safetensors`	Mistral 3 Small for Flux2	—

Note: The Ideogram 4 models were sourced from Comfy-Org/Ideogram-4 and added to this repository for convenience purposes.

📜 Licenses

Each model retains the original license from its respective base model. Please refer to the original model cards for licensing terms:

🙏 Acknowledgments

Comfy-Org for the quantization script and bf16 models
BobJohnson24 for ComfyUI-INT8-Fast and conversion tools
silveroxides for ComfyUI-QuantOps nodes
All original model authors and teams

Fontes

1 fonte

Hugging FacePrimárioVersão eb6682675836a42aa91fd4effcd77d68fe60ff42

huggingface.co/supermind/int8_convrot_models/tree/eb6682675836a42aa91fd4effcd77d68fe60ff42

Verificado 1 de out.

Artefatos de modelo

28 artefatos

checkpoints/ltx-2.3-22b-dev_int8_convrot.safetensors

safetensors · 23,9 GB · SHA-256 1853dbf29f63…47ba · Hugging Face

Baixar

diffusion_models/3d/pixal3d_int8_convrot.safetensors

safetensors · 5,20 GB · SHA-256 3003b0f95d6d…141f · Hugging Face

Baixar

diffusion_models/3d/trellis_2_int8_convrot.safetensors

safetensors · 4,89 GB · SHA-256 2c3efb637d48…20d7 · Hugging Face

Baixar

diffusion_models/flux/flux-2-dev_int8_convrot_quantops.safetensors

safetensors · 30,7 GB · SHA-256 e5febc3033a4…487c · Hugging Face

Baixar

diffusion_models/flux/flux-2-klein-4b_int8_convrot.safetensors

safetensors · 3,79 GB · SHA-256 f2ba417fcd5b…bb07 · Hugging Face

Baixar

diffusion_models/flux/flux-2-klein-9b_int8_convrot.safetensors

safetensors · 8,79 GB · SHA-256 031aa8bd2ebe…ffca · Hugging Face

Baixar

diffusion_models/flux/flux-2-klein-9b-kv_int8_convrot.safetensors

safetensors · 8,79 GB · SHA-256 c77a5030a03c…b672 · Hugging Face

Baixar

diffusion_models/flux/flux2-dev_int8_convrot_absmax.safetensors

safetensors · 30,8 GB · SHA-256 c4b7c7ff8aa4…b564 · Hugging Face

Baixar

diffusion_models/flux/flux2-dev_int8_convrot_mseclip.safetensors

safetensors · 30,8 GB · SHA-256 b4f9d748a38b…2096 · Hugging Face

Baixar

diffusion_models/ideogram/ideogram4_int8_convrot.safetensors

safetensors · 8,93 GB · SHA-256 a91640029434…163d · Hugging Face

Baixar

diffusion_models/ideogram/ideogram4_unconditional_int8_convrot.safetensors

safetensors · 8,93 GB · SHA-256 cd03ed94f244…c23d · Hugging Face

Baixar

diffusion_models/krea/krea2_raw_int8_convrot.safetensors

safetensors · 13,0 GB · SHA-256 d15476640b6e…a787 · Hugging Face

Baixar

diffusion_models/krea/krea2_turbo_int8_convrot.safetensors

safetensors · 13,0 GB · SHA-256 9377e6b8fea4…1777 · Hugging Face

Baixar

diffusion_models/qwen/qwen_image_2512_int8_convrot.safetensors

safetensors · 19,1 GB · SHA-256 cd6f8c0388cd…9ee2 · Hugging Face

Baixar

diffusion_models/qwen/qwen_image_edit_2511_int8_convrot.safetensors

safetensors · 19,1 GB · SHA-256 5fe66af54bdb…8eab · Hugging Face

Baixar

diffusion_models/z_image/z_image_int8_convrot.safetensors

safetensors · 5,75 GB · SHA-256 022661fa7ae8…64ff · Hugging Face

Baixar

diffusion_models/z_image/z_image_turbo_int8_convrot.safetensors

safetensors · 5,75 GB · SHA-256 d2f0574bb0a5…31c6 · Hugging Face

Baixar

text_encoders/gemma_2_2b_it_elm_int8_convrot.safetensors

safetensors · 2,99 GB · SHA-256 8f53c4e831c0…6a05 · Hugging Face

Baixar

text_encoders/gemma4_12b_int8_convrot.safetensors

safetensors · 12,2 GB · SHA-256 40c40e27e7e4…80dc · Hugging Face

Baixar

text_encoders/gemma4_e4b_it_int8_convrot.safetensors

safetensors · 10,8 GB · SHA-256 c6bfb2a0534a…7930 · Hugging Face

Baixar

text_encoders/mistral_3_small_flux2_int8_convrot.safetensors

safetensors · 17,2 GB · SHA-256 d058dded377b…2c4b · Hugging Face

Baixar

text_encoders/qwen_2.5_vl_7b_int8_convrot.safetensors

safetensors · 8,92 GB · SHA-256 5ae7646f584c…99c4 · Hugging Face

Baixar

text_encoders/qwen_3_4b_int8_convrot.safetensors

safetensors · 4,11 GB · SHA-256 60bd28906e4e…1c56 · Hugging Face

Baixar

text_encoders/qwen_3_8b_int8_convrot.safetensors

safetensors · 8,79 GB · SHA-256 d7c84f7e1b45…b4cc · Hugging Face

Baixar

text_encoders/qwen3.5_4b_int8_convrot.safetensors

safetensors · 4,98 GB · SHA-256 c09c01e44741…dcc0 · Hugging Face

Baixar

text_encoders/qwen3.5_9b_int8_convrot.safetensors

safetensors · 11,0 GB · SHA-256 ee6a6df6a6cf…9ca6 · Hugging Face

Baixar

text_encoders/qwen3vl_4b_int8_convrot.safetensors

safetensors · 4,53 GB · SHA-256 975604665916…e41a · Hugging Face

Baixar

text_encoders/qwen3vl_8b_int8_convrot.safetensors

safetensors · 9,37 GB · SHA-256 ae3439a4b4a0…f7df · Hugging Face

Baixar

Trechos de fonte

3 trechos

Readme11 de jul.huggingface.co/supermind/int8_convrot_models

--- license: other tags: - quantized - int8 - comfyui - diffusion_models - convrot - text_encoders --- # 📦 INT8 Quantized Model Collection (ConvRot) This repository contains a collection of popular generative models quantized to **INT8** using the **ConvRot** method for optimized inference with minimal quality loss. Almost all models were quantized from the original **BF16** weights using the `quant_int8_convrot.py` script with the `--mseclip` attribute for calibration. --- ## 🛠️ Quantization Details - **Base Precision:** BF16 → INT8 ConvRot - **Method:** ConvRot (Convolution Rotation) - **Calibration:** `--mseclip` for per-layer clipping optimization (couple has `--absmax`) - **Tool:** [`quant_int8_convrot.py`](https://github.com/Comfy-Org/comfy-model-tools/blob/main/quant_int8_convrot.py) (Comfy-Org) `flux-2-dev_int8_convrot_quantops.safetensors` was first quantized in ComfyUI using [ComfyUI-QuantOps](https://github.com/silveroxides/ComfyUI-QuantOps), then convert to `int8_convrot` format via [`convert_to_comfy.py`](https://github.com/BobJohnson24/ComfyUI-INT8-Fast/blob/main/convert_to_comfy.py) --- ## 📂 Included Models | Model Name | Original Source | Notes | |------------|----------------|-------| |**Checkpoints** |`ltx-2.3-22b-dev_int8_convrot.safetensors` | LTX 2.3 22B | — | | |**Diffusion models** | `flux-2-dev_int8_convrot_quantops.safetensors` | Flux-2 dev | via ComfyUI-INT8-Fast | | `flux-2-dev_int8_convrot_mseclip.safetensors` | Flux-2 dev | — | | `flux-2-dev_int8_convrot_absmax.safetensors` | Flux-2 dev | — | | `flux-2-klein-4b_int8_convrot.safetensors` | Flux-2 Klein 4B | — | | `flux-2-klein-9b_int8_convrot.safetensors` | Flux-2 Klein 9B | — | | `flux-2-klein-9b-kv_int8_convrot.safetensors` | Flux-2 Klein 9B KV | — | | `qwen_image_2512_int8_convrot.safetensors` | Qwen Image 2512 | — | | `qwen_image_edit_2511_int8_convrot.safetensors` | Qwen Image Edit 2511 | — | | `z_image_int8_convrot.safetensors` | Z-Image | — | | `z_image_turbo_int8_convrot.safetensors` | Z-Image Turbo | — | | `krea2_raw_int8_convrot.safetensors` | Krea 2 Raw | — | | `krea2_turbo_int8_convrot.safetensors` | Krea 2 Turbo | — | | `ideogram4_int8_convrot.safetensors` | Ideogram 4 | via dequant FP8 | | `ideogram4_unconditional_int8_convrot.safetensors` | Ideogram 4 Uncond. | via dequant FP8 | | |**3D models** | `trellis_2_int8_convrot.safetensors` | Trellis 2 | —...

Note1 de out.huggingface.co/supermind/int8_convrot_models

Source context: 0 downloads · 23 likes · Repo supermind/int8_convrot_models

Note16 de jul.huggingface.co/supermind/int8_convrot_models

Source context: 0 downloads · 6 likes · Repo supermind/int8_convrot_models