Black Forest Labs · 4B · 密集（Dense）
Fastest open FLUX.2 — sub-second text-to-image and multi-reference editing on consumer GPUs 看看你的 GPU 或 Mac 跑不跑得動 FLUX.2 Klein 4B——最低 2.2 GB，建議 3.7 GB。
2026-0132K context
| 量化 | 位元 | VRAM | 品質 | 狀態 |
|---|---|---|---|---|
| Q2_K | 2 | 1.8 GB | low | — |
| Q3_K_M | 3 | 2.3 GB | moderate | — |
| Q4_K_M | 4 | 2.5 GB | good | — |
| Q5_K_M | 5 | 3.1 GB | good | — |
| Q6_K | 6 | 3.6 GB | excellent | — |
| Q8_0 | 8 | 4.6 GB | excellent | — |
| F16 | 16 | 8.7 GB | lossless | — |
Can I run FLUX.2 Klein 4B locally?
- Can I run FLUX.2 Klein 4B locally?
- FLUX.2 Klein 4B needs about 2.2 GB of memory at a minimum and 3.7 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 FLUX.2 Klein 4B need?
- At Q4_K_M, FLUX.2 Klein 4B uses about 2.5 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.