mimo asr needs about 5.6 GB of memory at Q4_K (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 0.0 GB to 16.0 GB (F16).
MiMo-ASR: 8.02B‑parameter speech recognition model in GGUF format
MiMo-ASR is an 8.02‑billion‑parameter end‑to‑end automatic speech recognition model. It supports Mandarin, English, and code‑switching, and is optimized for robust transcription in noisy and multi‑speaker environments.
Good at
- Robust Mandarin and English transcription
- Code‑switching without language tags
- Song lyric recognition
Limits
- No vision support
- Requires 8‑k context for memory estimates
- MIT license only
Best for
- Transcribing meetings with multiple speakers
- Transcribing noisy audio recordings
- Generating lyrics from music tracks
Who it’s for. Developers building speech‑to‑text pipelines that need high accuracy across Mandarin and English. Researchers needing a large‑scale ASR model for benchmarking. Companies deploying on Apple Silicon, CPU, or CUDA without Python dependencies.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 4.5 GB | 5.6 GB | Fits | Get file → | |
| F16 | 16.0 GB | 18.5 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_K variant (4.52 GB file, ~5.6 GB memory at 8 k context). For 16‑GB VRAM, the F16 variant (16.04 GB file, ~18.5 GB memory) offers higher precision. The unknown quant is not recommended for production use.
What GPU do you need for mimo asr?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K (4.5 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K (4.5 GB file, about 5.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K (4.5 GB file, about 5.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K (4.5 GB file, about 5.6 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.0 GB file, about 18.5 GB in use).
Which mimo asr quant should you choose?
Q4_K (4.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mimo asr
How much VRAM does mimo asr need?
About 5.6 GB at Q4_K with an 8K context window. That is the 4.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run mimo asr on an 8 GB GPU?
Yes, with Q4_K: the 4.5 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mimo asr GGUF?
It depends on the quant: file is 0.0 GB, Q4_K is 4.5 GB, F16 is 16.0 GB.
Where can I download mimo asr GGUF?
The files are on Hugging Face in the cstr/mimo-asr-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does mimo asr use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MiMo-ASR on 8 GB VRAM?
Yes, the Q4_K variant uses 4.52 GB file size and requires about 5.6 GB memory at 8 k context.
Does MiMo-ASR support multi‑speaker transcription?
Yes, it is designed for accurate transcription of overlapping, multi‑party conversations.