higgs-tts-2-3b-base vs audio.cpp-gguf
Specs, VRAM requirements and download trends — updated 21 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | higgs-tts-2-3b-base | audio.cpp-gguf |
|---|---|---|
| Parameters | 5.8 B | — |
| Architecture | HiggsAudioV2ForConditionalGeneration | — |
| Context length | 2,048 | — |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 4 | — |
| Downloads 30d | 414,882 | 6,584,182 |
| Downloads all time | 4.4 M | 12.2 M |
| Quantizations on the Hub | SAFETENSORS | GGUF, SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-07-01 | 2026-07-14 |
Download trend
Daily snapshots, last 77 days (7 Aug – 22 Oct)
6.6 M368 K
higgs-tts-2-3b-base
audio.cpp-gguf
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
audio.cpp-gguf · fp16
1.6 GB / 24 GB
audio.cpp-gguf · Q4_0
4.7 GB / 24 GB
higgs-tts-2-3b-base · fp16
14.1 GB / 24 GB