MiniMax-H3 Pruned Ref-Delta Fused (GGUF)

GGUF quantizations for xmarre's MiniMax-H3-Pruned-Ref-Delta-Fused-r1024-ComfyUI.

This hybrid model fuses the crisp visual quality, motion dynamics, and clean audio of FL2VA with the persistent multi-image character conditioning of Ref2VA using a rank-1024 delta weight merge ($\Delta W_{r=1024}$) on the pruned 20.1B parameter MiniMax-H3 architecture.

With these GGUFs, you can now run reference-conditioned MiniMax-H3 locally on consumer GPUs (16 GB โ€“ 24 GB VRAM) with minimal quality loss.


File Overview

Filename Size Recommended GPU Description
MiniMax-H3-Pruned-Ref-Delta-Fused-Q8_0.gguf 21.6 GB 24 GB+ / Multi-GPU Near-indistinguishable from BF16 base
MiniMax-H3-Pruned-Ref-Delta-Fused-Q6_K.gguf 16.7 GB 24 GB VRAM High-fidelity sweet spot for critical renders
MiniMax-H3-Pruned-Ref-Delta-Fused-Q5_K_M.gguf 14.1 GB 16 GB โ€“ 24 GB VRAM Excellent balance of motion consistency and size
MiniMax-H3-Pruned-Ref-Delta-Fused-Q5_K_S.gguf 14.1 GB 16 GB VRAM Slightly smaller footprint with high precision
MiniMax-H3-Pruned-Ref-Delta-Fused-Q4_K_M.gguf 11.6 GB 16 GB VRAM Most Recommended. Fast, low VRAM, sharp details
MiniMax-H3-Pruned-Ref-Delta-Fused-Q4_K_S.gguf 11.6 GB 16 GB VRAM Lightweight 4-bit quantization
MiniMax-H3-Pruned-Ref-Delta-Fused-Q3_K_M.gguf 8.9 GB 12 GB โ€“ 16 GB VRAM Maximum VRAM savings for constrained setups

How to Use in ComfyUI

1. Install Node

Ensure you have the latest ComfyUI-GGUF custom node installed via ComfyUI Manager.

2. Place Files

Place the downloaded .gguf file into: ComfyUI/models/diffusion_models/ (or ComfyUI/models/unet/)

Recommended Generation Settings

With Turbo Acceleration (Fast Inference)

  • LoRA: minimax_h3_ref2v_turbo_8step_v1.0_768p_comfyui_resized_avg_rank_20_bf16.safetensors
  • LoRA Strength: 1.0 (or 0.85 if fine ripple noise occurs)
  • Steps: 8 steps
  • CFG: 1.0 (Do not exceed 1.2 with distilled turbo LoRAs)
  • Sampler: Euler
  • Scheduler: Beta or Simple
  • Resolution: 1280x720 (16:9) or 1280x544 (2.39:1)
  • Frame Count: 49 or 81 frames ($4k + 1$ rule)

Credits & Acknowledgements

Downloads last month
140
GGUF
Model size
20B params
Architecture
wan
Hardware compatibility
Log In to add your hardware

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Abiray/MiniMax-H3-Pruned-Ref-Delta-Fused-GGUF