Fish Audio Drama 3
Needs 50 GB at FP8 / INT8. The smallest real configuration today is 2× Tesla V100 32GB at Vast.ai, $0.14 per hour, about $99 a month at 730 hours.
- Per hour
- $0.14
- Per month
- $99
- Cheapest at
Vast.ai
What is documented about Fish Audio Drama 3
news checked 2026-10-2735B MoE text backbone with 3B active per token (initialised from Qwen3.5-35B-A3B per coverage), up to 16 speakers per request, voice cloning, natural-language direction, word-level edits; 83 languages per coverage. Files: 8 safetensors shards 39.60 GB + codec.pth 1.87 GB. On one H200: concurrency 16 RTF 0.373, concurrency 64 RTF 0.80. HF metadata still says fish-audio-research-license but the LICENSE file is the Community License dated 2026-10-13. HF repo created 2026-10-01; public launch 2026-10-13. Ranked #1 (Elo 1245, listed as 'Drama 3 Preview') on the Artificial Analysis open-weights TTS leaderboard read on 2026-10-27.
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice/open-weights
- https://huggingface.co/fishaudio/drama-3
- https://huggingface.co/api/models/fishaudio/drama-3?blobs=true
Memory · 1 precisionHow much VRAM it needs
Weights plus 20% runtime overhead. For voice models, activations also depend on resolution, clip length and batch size; the per-GPU estimates below give the practical configuration.
| Precision | Weights | Weights + headroom |
|---|---|---|
| FP8 + BF16published checkpoint | 42 GB | 50 GB |
Smallest configuration per GPU · 109 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| Tesla V100 32GBBest fit | 2× 32 GB64 GB total | 78% | $0.14 | $99 | Vast.aiTrust 78 · read Nov 2 · receipt · also Cyfuture AI $1.13, io.net $2.52 |
| Tesla P100 | 4× 16 GB64 GB total | 78% | $0.19 | $142 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.43 |
| RTX 3090 | 4× 24 GB96 GB total | 52% | $0.25 | $183 |  Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.56, Edgevana $0.92 |
| RTX 5060 Ti | 4× 16 GB64 GB total | 78% | $0.35 | $258 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.40, Edgevana $0.68 |
| RTX A4000 | 4× 16 GB64 GB total | 78% | $0.36 | $266 | Vast.aiTrust 78 · read Nov 2 · receipt · also AtmosCompute $0.66, Spheron $3.84 |
| RTX A6000 | 2× 48 GB96 GB total | 52% | $0.38 | $274 | Clore.aiTrust 49 · read Nov 2 · receipt · also Lium $0.84, Spheron $0.89 |
| Tesla V100 16GB | 4× 16 GB64 GB total | 78% | $0.38 | $275 | Vast.aiTrust 78 · read Nov 2 · receipt · also CloudRift $1.00, AtmosCompute $1.30 |
| Quadro RTX 5000 | 4× 16 GB64 GB total | 78% | $0.40 | $294 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 3060 | 8× 12 GB96 GB total | 52% | $0.43 | $312 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.64, AtmosCompute $1.01 |
| A800 80GB PCIe | 1× 80 GB80 GB total | 62% | $0.47 | $342 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Quadro RTX 8000 | 2× 48 GB96 GB total | 52% | $0.48 | $354 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.56 |
| RTX 3070 | 8× 8 GB64 GB total | 78% | $0.50 | $364 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $5.23 |
| L40 | 2× 48 GB96 GB total | 52% | $0.54 | $391 | Vast.aiTrust 78 · read Nov 2 · receipt · also io.net $1.32, GPU.ai $1.56 |
| RTX 2080 Ti | 8× 11 GB88 GB total | 57% | $0.59 | $432 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.68 |
| T4 | 4× 16 GB64 GB total | 78% | $0.59 | $434 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $0.78, NHN Cloud $2.46 |
| A100 80GB | 1× 80 GB80 GB total | 62% | $0.60 | $440 | Vast.aiTrust 78 · read Nov 2 · receipt · also packet.ai $0.89, GPUBank $0.95 |
| RTX 5060 | 8× 8 GB64 GB total | 78% | $0.65 | $472 | Clore.aiTrust 49 · read Nov 2 · receipt |
| RTX PRO 6000 | 1× 96 GB96 GB total | 52% | $0.66 | $482 |  packet.ainot scored · read Nov 2 · receipt · also Runpod $0.69, HyperAI $0.80 |
| Titan RTX | 4× 24 GB96 GB total | 52% | $0.70 | $508 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 5070 Ti | 4× 16 GB64 GB total | 78% | $0.70 | $508 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.80, Edgevana $0.80 |
| RTX 4070 Ti Super | 4× 16 GB64 GB total | 78% | $0.75 | $548 | Clore.aiTrust 49 · read Nov 2 · receipt · also AtmosCompute $1.54 |
| L40S | 2× 48 GB96 GB total | 52% | $0.76 | $555 |  LiumTrust 40 · read Nov 2 · receipt · also Vast.ai $1.07, CloudRift $1.26 |
| A100 40GB | 2× 40 GB80 GB total | 62% | $0.77 | $566 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $1.83, AtmosCompute $1.93 |
| RTX 5090 | 2× 32 GB64 GB total | 78% | $0.80 | $586 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.96, Edgevana $1.35 |
| The 24 cheapest of 69 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
Fish Audio Drama 3 · related