s1-mini-GGUF
GGUF builds of superwhisper/s1-mini, release v1, for llama.cpp, Ollama, LM Studio, and anything else built on llama.cpp. You can use it in your own dictation app too, just check the license first.
Params
—
Context
—
Downloads 30d
241 K
Likes
46
Download history
daily snapshots · 30 days293 K194 K
Sep 25Oct 5Oct 15Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| s1-mini-q4_k_m.gguf | Q4_K_M | 0.5 GB | 1.0 GB | ✅ Runs comfortably |
| s1-mini-f16.gguf | GGUF | 1.5 GB | 2.2 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run s1-mini-gguf # pin the quantization explicitly $ ollama run s1-mini-gguf-q4_k_m
$ huggingface-cli download superwhisper/s1-mini-GGUF-GGUF \
s1-mini-q4_k_m.gguf --local-dir .
$ llama-cli -m s1-mini-q4_k_m.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/s1-mini-gguf
{
"hf_id": "superwhisper/s1-mini-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 240899,
"vram_estimates": [
{ "quant": "GGUF", "gb": 2.2 },
{ "quant": "Q4_K_M", "gb": 1.0 }
],
"updated_at": "2026-09-25T01:00:24Z"
}
Specifications
- Licence
- other
- First seen on the Hub
- 2026-08-12
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-25
Compare with any text-generation model