Which quant should I pick?

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.

Save my rig

2 · Model & context

Lower precision shrinks the KV cache (fits more context).

Hunyuan-A13B-Instruct quants, ranked

Full model page & downloads →
Pick your GPU above to see which of these fit, plus estimated speeds. Sizes and the quality guidance below don't need a rig.
  1. GGUF · Q8_0
    79.58 GB

    Effectively lossless in community experience — the closest you get to the original model, at the largest practical GGUF size.

    Note: Bartowski Q8_0 quant of Hunyuan-A13B-Instruct (80.393B-A13B MoE) — high-quality option. Tencent Hunyuan Community License (territory-restricted: excludes EU/UK/South Korea). 3-part split GGUF (load via -00001-of-00003).

  2. GGUF · Q5_K_M
    53.64 GB

    High quality with a noticeably smaller footprint than Q6 — a popular 'quality first, but it still fits' pick.

    Note: Bartowski Q5_K_M quant of Hunyuan-A13B-Instruct (80.393B-A13B MoE) — quality step-up. Tencent Hunyuan Community License (territory-restricted: excludes EU/UK/South Korea). 2-part split GGUF (load via -00001-of-00002).

  3. GGUF · Q4_K_M Community default
    45.93 GB

    The community default: minor quality loss versus Q5/Q6, usually unnoticeable outside edge tasks, at a much smaller size.

    Note: Bartowski Q4_K_M quant of Hunyuan-A13B-Instruct (80.393B-A13B MoE) — recommended balanced pick. Tencent Hunyuan Community License (territory-restricted: excludes EU/UK/South Korea).

  4. GGUF · IQ4_XS
    40.50 GB

    An i-quant that packs 4-bit weights tighter than Q4_K_S — similar quality in community reports and a smaller file, though slightly heavier to decode on some runtimes.

    Note: Bartowski IQ4_XS quant of Hunyuan-A13B-Instruct (80.393B-A13B MoE) — compact low-bit option. Tencent Hunyuan Community License (territory-restricted: excludes EU/UK/South Korea).

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.