Catalogue
Everything the NeuroBrix runtime executes today, grouped by category. One engine, one .nbx format, the same commands for every row on this page.
Open any model for its container facts, browse the model hub with search and filters, orinstall the runtime.
- 49
- models
- 10
- categories
- 9
- runtime families
- 27
- publishers
- 984.5 GiB
- packaged
Generated from the hub database at . The same rows are served by /api/models.
| Model | Licence | Size | Downloads |
|---|---|---|---|
| TinyLlama/TinyLlama-1.1B-Chat-v1.0 | apache-2.0 | 2.1 GiB | 70 |
| Qwen/Qwen3-30B-A3B-Thinking-2507 | apache-2.0 | 56.9 GiB | 31 |
| deepseek-ai/deepseek-moe-16b-chat | deepseek | 30.5 GiB | 20 |
| ibm-granite/granite-3.1-1b-a400m-instruct | apache-2.0 | 2.6 GiB | 17 |
$ neurobrix import TinyLlama/TinyLlama-1.1B-Chat-v1.0 # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | deepseek | 29.9 GiB | 38 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct | apache-2.0 | 56.9 GiB | 28 |
$ neurobrix import deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| zai-org/GLM-4.1V-9B-Thinking | mit | 19.2 GiB | 28 |
$ neurobrix import zai-org/GLM-4.1V-9B-Thinking # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| Qwen/Qwen3-VL-30B-A3B-Thinking | apache-2.0 | 57.9 GiB | 33 |
| deepseek-ai/Janus-Pro-7B | mit | 13.8 GiB | 25 |
| Qwen/Qwen3-Omni-30B-A3B-Instruct | apache-2.0 | 65.8 GiB | 23 |
| openbmb/MiniCPM-o-4_5 | apache-2.0 | 19.3 GiB | 21 |
| inclusionAI/Ming-Lite-Omni-1.5 | mit | 51.1 GiB | 16 |
$ neurobrix import Qwen/Qwen3-VL-30B-A3B-Thinking # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| ResembleAI/chatterbox | mit | 2 GiB | 156 |
| hexgrad/Kokoro-82M | apache-2.0 | 352.9 MiB | 29 |
| fishaudio/s1-mini | cc-by-nc-sa-4.0 | 2.6 GiB | 22 |
| canopylabs/orpheus-3b-0.1-ft | apache-2.0 | 14.1 GiB | 19 |
| microsoft/VibeVoice-1.5B | mit | 5 GiB | 17 |
$ neurobrix import ResembleAI/chatterbox # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| openai/whisper-large | mit | 5.8 GiB | 70 |
| openai/whisper-large-v3-turbo | mit | 1.5 GiB | 53 |
| nvidia/parakeet-tdt-1.1b | cc-by-4.0 | 4 GiB | 21 |
$ neurobrix import openai/whisper-large # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| ibm-granite/granite-speech-3.3-8b | apache-2.0 | 16.1 GiB | 27 |
| nvidia/canary-qwen-2.5b | cc-by-4.0 | 4.7 GiB | 21 |
| mistralai/Voxtral-Mini-3B-2507 | apache-2.0 | 8.7 GiB | 20 |
$ neurobrix import ibm-granite/granite-speech-3.3-8b # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers | nvidia-open-model-license | 9 GiB | 49 |
| PixArt-alpha/PixArt-Sigma-XL-2-1024-MS | openrail++ | 20.3 GiB | 42 |
| PixArt-alpha/PixArt-XL-2-1024-MS | openrail++ | 20.3 GiB | 35 |
| ostris/Flex.1-alpha | apache-2.0 | 24.5 GiB | 23 |
| Efficient-Large-Model/Sana_1600M_4Kpx_BF16_diffusers | nvidia-open-model-license | 12 GiB | 4 |
$ neurobrix import Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| JingyunLiang/SwinIR-001_classicalSR_DIV2K_s48w8_SwinIR-M_x4 | apache-2.0 | 43.2 MiB | 30 |
| caidas/swin2SR-classical-sr-x2-64 | apache-2.0 | 47.1 MiB | 27 |
| xinntao/Real-ESRGAN-RealESRGAN_x4plus | bsd-3-clause | 63.9 MiB | 26 |
| XPixelGroup/HAT-HAT-L_SRx4_ImageNet-pretrain | apache-2.0 | 145.8 MiB | 25 |
| caidas/swin2SR-classical-sr-x4-64 | apache-2.0 | 47.6 MiB | 24 |
| caidas/swin2SR-realworld-sr-x4-64-bsrgan-psnr | apache-2.0 | 46.9 MiB | 21 |
| JingyunLiang/SwinIR-001_classicalSR_DF2K_s64w8_SwinIR-M_x2 | apache-2.0 | 42.7 MiB | 21 |
| XPixelGroup/HAT-HAT-S_SRx4 | apache-2.0 | 34.8 MiB | 15 |
| ai-forever/Real-ESRGAN-RealESRGAN_x2 | — | 63.9 MiB | 14 |
| ai-forever/Real-ESRGAN-RealESRGAN_x8 | — | 64 MiB | 11 |
$ neurobrix import JingyunLiang/SwinIR-001_classicalSR_DIV2K_s48w8_SwinIR-M_x4 # then serve, run, stop
| Model | Licence | Size | Downloads |
|---|---|---|---|
| Wan-AI/Wan2.1-T2V-1.3B-Diffusers | apache-2.0 | 26.9 GiB | 51 |
| zai-org/CogVideoX-2b | apache-2.0 | 12.9 GiB | 41 |
| Wan-AI/Wan2.2-I2V-A14B-Diffusers | apache-2.0 | 118 GiB | 39 |
| Wan-AI/Wan2.1-I2V-14B-480P-Diffusers | apache-2.0 | 84.4 GiB | 30 |
| hpcai-tech/Open-Sora-v2 | apache-2.0 | 42.4 GiB | 27 |
| rhymes-ai/Allegro | apache-2.0 | 23.6 GiB | 25 |
| rhymes-ai/Allegro-TI2V | apache-2.0 | 24.3 GiB | 24 |
| genmo/mochi-1-preview | apache-2.0 | 38.2 GiB | 23 |
| Wan-AI/Wan2.1-VACE-1.3B-diffusers | apache-2.0 | 18.2 GiB | 21 |
| zai-org/CogVideoX-5b-I2V | cogvideox-license | 21 GiB | 18 |
| Efficient-Large-Model/SANA-Video_2B_720p_diffusers | nvidia-open-model-license | 17.1 GiB | 13 |
$ neurobrix import Wan-AI/Wan2.1-T2V-1.3B-Diffusers # then serve, run, stop