Downloads · 30 days
33.8K
55% of all-time downloads
minimax-h3-turbo-GGUF
ChrisColeTech/minimax-h3-turbo-GGUF
minimax-h3-turbo-GGUF is a text-to-video model from ChrisColeTech. Use it when you need video from a text prompt. It is set up for gguf. The card lists the license as other.
The MiniMax H3 FL2VA (pruned) DiT with the LightX2V Turbo 8-step v1.0 LoRA baked in.
All-time downloads
61.2K
Public
Repo size
146 GB
Likes
24
Public
Repo makeup
Click a slice to open those files.
.gguf86 GB · 66%
At a glance
- Task
- Text-to-Video
- Library
- gguf
- License
- other
- Access
- Public
- Created
- Aug 11, 2026
- Updated
- Oct 15, 2026
- SHA
- 490f6dca
Base models
Model card
From the Hugging Face model README
MiniMax H3 Turbo Merge GGUF (8-step LoRA baked-in)
The MiniMax H3 FL2VA (pruned) DiT with the LightX2V Turbo 8-step v1.0 LoRA baked in.
and
The MiniMax H3 REF2VA (pruned) DiT with the LightX2V Turbo 4-step v1.0 LoRA baked in.
Modes: img2video, txt2video, FL2VA / T2VA / I2VA / REF2VA.
Samples (4B vs 8B Text Encoder)
Both samples use the same turbo Q4_K_M turbo GGUF diffusion model, prompt, and settings, only the text encoder changes (4B vs 8B).
4B Text Encoder + ClipProj (8-steps)
<video controls width="700" src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/txt2video-red-car-4b-clipproj-q6.mp4"></video>
- (~2.3 min) on an RTX 5090 (32 GB).
Components used to generate
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | minimax_h3_fl2va_turbo_Q4_K_M.gguf | 11.4 GB | Link |
| 4B Text Encoder | qwen3vl_4b_fp8_scaled.safetensors | 5.24 GB | Link |
| 4B Clip Proj | mmh3-4b-ClipProj-v3-mlp.safetensors | 304 MB | Link |
| Video VAE | minimax_h3_video_vae_fp16.safetensors | 5.21 GB | Link |
| Audio VAE | minimax_h3_audio_vae_fp32.safetensors | 605 MB | Link |
8B Text Encoder + ClipProj (8-steps)
<video controls width="700" src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/txt2video-red-car-8b-clipproj-q6.mp4"></video>
- (~2.5 min) on an RTX 5090 (32 GB).
Components used to generate
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | minimax_h3_fl2va_turbo_Q4_K_M.gguf | 11.4 GB | Link |
| 8B Text Encoder | qwen3vl_8b_fp8_scaled.safetensors | 10.6 GB | Link |
| 8B Clip Proj | mmh3-8b-ClipProj-v3-mlp.safetensors | 386 MB | Link |
| Video VAE | minimax_h3_video_vae_fp16.safetensors | 5.21 GB | Link |
| Audio VAE | minimax_h3_audio_vae_fp32.safetensors | 605 MB | Link |
Sample settings
| Parameter | Value |
|---|---|
| Prompt | cinematic tracking shot of a red sports car on a wet night street, neon reflections, engine rumble and rain on asphalt, shallow depth of field |
| Resolution | 1280 × 720 |
| Frames | 90 frames → ~3.75 s |
| Steps | 8 |
| CFG | 1.0 |
| Seed | 42 |
Image-to-Video (8-steps)
<table style="text-align: -webkit-center"> <tr > <td style="align-content: center;text-align: center"><img src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/ComfyUI_00003.png" style="width:400px"></td> <td style="align-content: center;text-align: center"><video controls src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/minimax-h3-turbo_00013_.mp4" style="height:400px;"></video></td></tr> <tr><td colspan=2 style="align-content: center;text-align: center"><strong>Prompt:</strong> <br>Use this image as the first frame. <br>Make her fly. Full body shot. <br>High quality</td></tr> </table>Link to workflow Link
Components used to generate
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | minimax_h3_fl2va_turbo_Q4_K_M.gguf | 11.4 GB | Link |
| 8B Text Encoder | qwen3vl_8b_fp8_scaled.safetensors | 10.6 GB | Link |
| 8B Clip Proj | mmh3-8b-ClipProj-v3-mlp.safetensors | 386 MB | Link |
| Video VAE | minimax_h3_video_vae_fp16.safetensors | 5.21 GB | Link |
| Audio VAE | minimax_h3_audio_vae_fp32.safetensors | 605 MB | Link |
REF2VA works with up to 9 input images
<table style="text-align: -webkit-center"> <tr><td style="height:300px; justify-items: center"><img src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/a-red-vintage-car-parked-on-a-sunny-cobblestone-street-blue-20260813-031631.png" style="height:300px; justify-items: center" ></td><td style="height:300px; justify-items: center"><img src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/a-solitary-glass-greenhouse-on-a-foggy-cliff-edge-at-dawn-20260808-122900.webp" style="height:300px"></td></tr> <tr><td style="height:300px; justify-items: center"><img src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/an-astronaut-sitting-in-a-field-of-tall-wildflowers-holding-20260808-123526.webp" style="height:300px; justify-items: center"></td><td style="height:300px; justify-items: center"><img src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/close-up-portrait-of-an-elderly-fisherman-with-weathered-20260808-123813.webp" style="height:300px"></td></tr> </table> <video controls src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/ComfyUI_00008_.mp4" style="height:400px;"></video>Components used to generate
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | minimax_h3_ref2va_turbo_Q4_K_M.gguf | 11.4 GB | Link |
| 8B Text Encoder | qwen3vl_8b_fp8_scaled.safetensors | 10.6 GB | Link |
| 8B Clip Proj | mmh3-8b-ClipProj-v3-mlp.safetensors | 386 MB | Link |
| Video VAE | minimax_h3_video_vae_fp16.safetensors | 5.21 GB | Link |
| Audio VAE | minimax_h3_audio_vae_fp32.safetensors | 605 MB | Link |
⚠ Must use the updated GGUF Loader ⚠
In comfy:
- Open the ComfyUI Manager
- Change the channel to "Channel (remote)"
- and search for comfyui-gguf-loader
Use the turbo workflow Link
Recommended settings (turbo 8-step)
| Parameter | Value | Notes |
|---|---|---|
width × height | 1280 × 720 | 720P max resolution |
num_frames | 124 | 481 max frames |
frame_rate | 24.0 | |
steps / NFE | 8 | 8-steps minimum, 16 steps max |
guidance / CFG | 1.0 | always use 1.0 for turbo variants |
negative_prompt | (empty in samples) | optional |
Sources
| Base DiT | MiniMax H3 FL2VA pruned fp8_scaled — family of MiniMaxAI/MiniMax-H3 |
| Turbo LoRA | LightX2V FL2VA Turbo 8-step v1.0 (ComfyUI) — minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors |
| Turbo weights | lightx2v/Minimax-h3-Turbo |
| Turbo docs / code | ModelTC/Minimax-H3-Turbo · LightX2V |
| Upstream 8-step specs | FL2VA / T2VA · train 544p mixed AR · video/audio shifts 12 / 3 · distill 8 NFE · recommended inference 8 (upstream also lists 4 for this LoRA) |
| This bake | Offline fuse @ strength 1.0 (208/208 keys) → stochastic re-FP8 → GGUF ladder |
| Runtime LoRA | Not required — already fused into these files |
Notes
- Known Limitations Here
- ComfyUI + 4B/8B: matching
mmh3-*-ClipProj-celeb-mlpis REQUIRED for small TEs. - Audio is first-class on H3 — sample mp4s include stereo AAC.
- Frame grid:
num_frames % 17 == 5(90 and 124 are valid). - MiniMax H3 — custom / other terms; read upstream before commercial use.
- LightX2V turbo LoRA — see lightx2v/Minimax-h3-Turbo and ModelTC/Minimax-H3-Turbo.
- Qwen3-VL — Apache-2.0 (Alibaba).
- ClipProj — MIT code (nicolab28/ComfyUI-ClipProj); matrices per NicoLab’s card.
- Task
- Text-to-Video
- Library
- gguf
- License
- other
- Created
- Aug 11, 2026
- Updated
- Oct 15, 2026