Can you run Coqui XTTS-v2 locally?

XTTS family · November 2023 · 0.75B parameters · Hugging Face model card

How much VRAM does Coqui XTTS-v2 need at each quantization?

Coqui XTTS-v2 needs 1.0 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level including runtime overhead.

GPT-style decoder + vocoder — no growing KV cache for synthesis. Table adds a 0.5 GB runtime overhead. Parameter count estimated from the 2.1 GB FP16 checkpoint on the HF repo (Coqui does not publish an exact figure).

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (not applicable to this architecture). Source: ≈0.75B parameters (estimated from 2.09 GB FP16 repo size), 17 languages, 6-second voice cloning — HF model card (coqui/XTTS-v2).

Which GPUs can run Coqui XTTS-v2 locally?

At Q4_K_M with a 4k context, Coqui XTTS-v2 needs 1.0 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs Coqui XTTS-v2 comfortably (25%+ VRAM headroom)

Can a Mac run Coqui XTTS-v2?

Yes — these Apple Silicon machines fit Coqui XTTS-v2 at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can Coqui XTTS-v2 run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Coqui XTTS-v2 at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run Coqui XTTS-v2?

These mini PCs and workstations from our database fit Coqui XTTS-v2 at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions

Related guides

• Best GPU for Whisper
• Best GPU Under $500
• VRAM Calculator