Aiqre

Model library / superwhisper

s1-mini

S1-mini is a 0.6 B-parameter text normaliser that cleans raw English ASR output into properly punctuated, capitalised written text.

752M

Parameters in total

40,960

Context length in tokens, as published

1 GiB

Weights at the released precision

other

Licence declared on the repository

Overview

What this model is.

Superwhisper's S1-mini is a 0.6 B-parameter text normaliser that rewrites raw speech-to-text transcripts into clean written English, removing fillers, correcting false starts, and applying punctuation, capitalization and appropriate rendering of numbers, dates, times, currency and email addresses as described by the publisher for downstream dictation applications.

The model contains 752 million unique parameters and is stored in bfloat16 format. Its context window spans 40,960 tokens. The quantised GGUF build is 462 MiB and runs comfortably on a laptop CPU; GPU use is possible via `device_map="auto"`. The licence is listed as "other", and the model type is qwen3 without expert layers.

Specification

The published shape.

Repositorysuperwhisper/s1-mini
Publishersuperwhisper
Published12 August 2026
ArchitectureQwen3ForCausalLM
Model typeqwen3
Parameters751,632,384
Layers28
Hidden size1,024
Attention heads16, 8 key/value heads
Context length40,960 tokens
Vocabulary151,936 tokens
Weight formatbfloat16
Licenceother
Base modelQwen/Qwen3-0.6B

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf161.4 GiBFull precision as released
fp80.7 GiB8-bit, near-lossless on most models
int40.4 GiB4-bit, smallest footprint

The cache costs 112 KiB per token at 16-bit, so the full 40,960-token context of one request needs about 4.4 GiB. Concurrency multiplies that number, not the weights.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB 1 17.7 GiB the full 40,960 tokens
RTX 5090 32GB 1 24.9 GiB the full 40,960 tokens
L40S 48GB 1 39.3 GiB the full 40,960 tokens
A100 80GB 1 68.1 GiB the full 40,960 tokens
H100 80GB 1 68.1 GiB the full 40,960 tokens
RTX PRO 6000 96GB 1 82.5 GiB the full 40,960 tokens
H200 141GB 1 123.0 GiB the full 40,960 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve superwhisper/s1-mini \
  --max-model-len 40960 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does s1-mini need?

The weights take about 1 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 18 GiB for the key-value cache.

What licence does s1-mini use?

The repository declares other. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 40,960 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

IFM/K2-Horizon-0.9B

K2-Horizon-0.9B is a 1.1 billion-parameter dense decoder-only model with a 128 k token context window.

Nanbeige/Nanbeige4.2-3B-DSpark

Nanbeige4.2-3B is a compact agentic language model designed for reasoning, tool use and personal-assistant tasks.

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.