Instructions to use DeepBeepMeep/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use DeepBeepMeep/MiniMax-H3 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
Add MiniMax H3 text encoder provenance
Browse files
Qwen3-VL-32B-Instruct/TEXT_ENCODER_SOURCES.txt
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MiniMax H3 text encoder provenance
|
| 2 |
+
==================================
|
| 3 |
+
|
| 4 |
+
Qwen3-VL-32B-Instruct-layer50_bf16.safetensors
|
| 5 |
+
Source model: https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct
|
| 6 |
+
Preparation: constructed locally from the upstream Qwen checkpoint by retaining the visual encoder, token embedding, and first 50 language layers.
|
| 7 |
+
SHA256: a91ca0cc41bead2e62d8fc044a3ffdbd9487daa7c8997f697049990c7178e0a6
|
| 8 |
+
|
| 9 |
+
Qwen3-VL-32B-Instruct-layer50_quanto_bf16_int8.safetensors
|
| 10 |
+
Source artifact: Qwen3-VL-32B-Instruct-layer50_bf16.safetensors
|
| 11 |
+
Preparation: quantized locally with MMGP/Quanto; this artifact was not downloaded from a separate upstream URL.
|
| 12 |
+
SHA256: 4df8fc5237746b3b058745d6ec8fe1e54a9721bdc663d35d2d1806952672f301
|
| 13 |
+
|
| 14 |
+
qwen3vl-32B-MiniMax-H3-Q2_K.gguf
|
| 15 |
+
Downloaded from: https://huggingface.co/realrebelai/MiniMax-H3_GGUFs/resolve/main/qwen3vl-32B-MiniMax-H3-Q2_K.gguf
|
| 16 |
+
SHA256: 5bbc11d0b3ef197c98df2ce8f05de8fbb8eb5917cd91c33d0b59f93759b34914
|
| 17 |
+
|
| 18 |
+
qwen3vl-32B-MiniMax-H3-Q4_K_M.gguf
|
| 19 |
+
Downloaded from: https://huggingface.co/realrebelai/MiniMax-H3_GGUFs/resolve/main/qwen3vl-32B-MiniMax-H3-Q4_K_M.gguf
|
| 20 |
+
SHA256: 1bf75e038c5895b97b6ea16cc1e3d32076254b06ec3df10657650d86dc82279e
|
| 21 |
+
|
| 22 |
+
qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
|
| 23 |
+
Downloaded from: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
|
| 24 |
+
SHA256: 35a88d51044231fe332301d7a62aa81e3f2cba62febeb446e2c1e3e0ef76f2c6
|
| 25 |
+
|
| 26 |
+
Tokenizer and configuration side files
|
| 27 |
+
--------------------------------------
|
| 28 |
+
config.json, tokenizer.json, preprocessor_config.json, chat_template.json, and vocab.json originate from:
|
| 29 |
+
https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct
|
| 30 |
+
|
| 31 |
+
tokenizer_config.json was taken from the MiniMax H3 text encoder package at revision 73372e6cf53e414edd3ab03e357717fb0602e758:
|
| 32 |
+
https://huggingface.co/MiniMaxAI/MiniMax-H3/resolve/73372e6cf53e414edd3ab03e357717fb0602e758/text_encoder/tokenizer_config.json
|