Pick your GPU and a model, and we'll rank its quants from highest to lowest quality —
with the fit verdict, size, an estimated speed, and a plain-English note on what you give up
at each step down. No account needed.
1 · Your GPU
No matching GPU in the list — you can type the model manually.
Search for your card above (Apple Silicon routes to unified memory automatically).
Without a GPU we'll still show sizes and the quality guidance below.
Used to judge partial CPU offload when a quant overflows VRAM.
Save your rig for one-click answers.
Your rig lives in this browser. A free account keeps it across the calculator, model pages and this helper.
Pick your GPU above to see which of these fit, plus estimated speeds. Sizes and the quality guidance below don't need a rig.
safetensors · BF16Community default
3.59 GB
Full 16-bit (bfloat16) weights: no quantization loss, but about twice an 8-bit quant's size.
Note: BF16 source weights (official Qwen3-TTS-12Hz-1.7B-Base) — reference TTS artifact. GGUF community-only; safetensors is the universal format (Transformers/vLLM). Bundles speech_tokenizer codec (+682MB) + tokenizer/config.
Verdicts and sizes match this model's page exactly. Speeds are roofline estimates (a range, not a promise).
Quality notes reflect community experience, not measured benchmarks.