MI

s1 mini

MiniGGUF by superwhisperUpdated 2026-08-28
Download on Hugging Face
Parameters752M
Context40K
Layers28
Architectureqwen3
Smallest quant0.5 GB
Quick answer

s1 mini needs about 1.9 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB (Q4_K_M) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

0.6B text normalizer for speech-to-text output

S1 mini is a 0.6B‑parameter model that normalizes raw ASR transcripts. It removes fillers, resolves false starts, adds punctuation and capitalization, and formats numbers, dates, times, currency and email addresses. The model is trained on 40,960‑token context and runs on CPU or GPU via llama.cpp.

Good at

  • Clean ASR transcripts
  • Punctuation and capitalization
  • Formatting dates and numbers

Limits

  • English only
  • Not a chat model
  • Requires control line in input

Best for

  • Dictation apps
  • Transcription cleanup
  • Voice‑to‑text pipelines

Who it’s for. Developers building voice‑to‑text or dictation applications that need clean, formatted text from raw ASR output. The model is lightweight and can run on laptops or embedded devices.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M build (0.48 GB file, ~1.9 GB memory at 8 k context). If more VRAM is available, the F16 build (1.51 GB file, ~2.9 GB memory) offers higher precision. Both builds are suitable for CPU use as well.

What GPU do you need for s1 mini?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 F16 (1.5 GB file, about 2.9 GB in use).

Which s1 mini quant should you choose?

Q4_K_M is the usual starting point for s1 mini: it balances file size and quality well. Here it is a 0.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters752M
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized bysuperwhisper
FamilyMini
Licenseother
Downloads (HF)234,200
Last updated2026-08-28

Frequently asked questions about s1 mini

How much VRAM does s1 mini need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.5 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 s1 mini on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of s1 mini GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, F16 is 1.5 GB.

What context length does s1 mini support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download s1 mini GGUF?

The files are on Hugging Face in the superwhisper/s1-mini-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 s1 mini use?

Hugging Face lists the license as other. 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 S1 mini on a laptop CPU?

Yes, the Q4_K_M build runs comfortably on a laptop CPU with about 1.9 GB RAM at 8 k context.

Does S1 mini support multiple languages?

No, it is trained only on English data.

Is there a chat interface?

No, S1 mini is not a chat model and requires a control line at the top of the input.

Other GGUFs of s1-mini

Similar models

Browse all →

More Mini models

All Mini →

Other tiny models

All tiny models →