Perplexity · 4.5B · Dense
pplx-decider distilled into Qwen 3.5 4B — the same API and image support at a seventh of the size Check if your GPU or Mac can run pplx-decider Flash v1.2 locally — 2.5 GB min, 4.2 GB recommended.
2026-10256K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 1.9 GB | low | — |
| Q3_K_M | 3 | 2.5 GB | moderate | — |
| Q4_K_M | 4 | 2.8 GB | good | — |
| Q5_K_M | 5 | 3.4 GB | good | — |
| Q6_K | 6 | 4 GB | excellent | — |
| Q8_0 | 8 | 5.1 GB | excellent | — |
| F16 | 16 | 9.7 GB | lossless | — |
Can I run pplx-decider Flash v1.2 locally?
- Can I run pplx-decider Flash v1.2 locally?
- pplx-decider Flash v1.2 needs about 2.5 GB of memory at a minimum and 4.2 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 Flash v1.2 need?
- At Q4_K_M, pplx-decider Flash v1.2 uses about 2.8 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.