Perplexity · 26B · Dense
Perplexity's decision model on Qwen 3.8 27B — answers every question about a request in one pass, text and images Check if your GPU or Mac can run pplx-decider v1.2 locally — 14.6 GB min, 24.3 GB recommended.
2026-10256K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 8.9 GB | low | — |
| Q3_K_M | 3 | 12.2 GB | moderate | — |
| Q4_K_M | 4 | 13.9 GB | good | — |
| Q5_K_M | 5 | 17.2 GB | good | — |
| Q6_K | 6 | 20.6 GB | excellent | — |
| Q8_0 | 8 | 27.2 GB | excellent | — |
| F16 | 16 | 54 GB | lossless | — |
Can I run pplx-decider v1.2 locally?
- Can I run pplx-decider v1.2 locally?
- pplx-decider v1.2 needs about 14.6 GB of memory at a minimum and 24.3 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does pplx-decider v1.2 need?
- At Q4_K_M, pplx-decider v1.2 uses about 13.9 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.