Model Intelligence Sheet
smthem/comfy-org-gguf-int4 overview
All base model is from @comfy org https://huggingface.co/Comfy Org Quant comfy org origin bf16 model to gguf or convrot int4 Convrot int4 use origin comfyUI wo…
Runs locally from ~6.43 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
13 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Boogu-Image-0.1-Edit-Turbo-0708-hotfix-Q8_0.gguf | GGUF | Q8_0 | 11.40 GB | Download |
| boogu_image_edit_turbo-Q8_0.gguf | GGUF | Q8_0 | 11.40 GB | Download |
| firered_image_edit_1.0-mix-Q4_K_S.gguf | GGUF | Q4_K_S | 15.67 GB | Download |
| krea2_turbo-Q8_0.gguf | GGUF | Q8_0 | 14.15 GB | Download |
| minimax_h3_fl2va_unflatten-adaln-Q6_K.gguf | GGUF | Q6_K | 29.27 GB | Download |
| minimax_h3_fl2va_unflatten-adaln_Q4_K_S.gguf | GGUF | Q4_K_S | 24.64 GB | Download |
| minimax_h3_ref2va-unflatten-adaln_Q4_K_S.gguf | GGUF | Q4_K_S | 24.64 GB | Download |
| qwen3vl_32b_minimax_h3-Q4_K_S.gguf | GGUF | Q4_K_S | 15.34 GB | Download |
| qwen_image_edit_2511-mix-Q4_K_S.gguf | GGUF | Q4_K_S | 15.67 GB | Download |
| wan2.1-t2v-14b-Q6_K.gguf | GGUF | Q6_K | 11.62 GB | Download |
| wan2.2_bernini_r_high_noise-Q6_K.gguf | GGUF | Q6_K | 10.93 GB | Download |
| wan2.2_bernini_r_low_noise-Q6_K.gguf | GGUF | Q6_K | 13.63 GB | Download |
| z_image_turbo_Q8_0.gguf | GGUF | Q8_0 | 6.43 GB | Download |
Model Details
Model README
---
license: mit
---
#
All base model is from @comfy-org
Quant comfy-org origin bf16 model to gguf or convrot-int4
Convrot -int4 use origin comfyUI workflows
gguf use node:
gguf node link or @city96
Run smthem/comfy-org-gguf-int4 with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models