All models › bfl
flux-2-klein-4b
bfl · Apache 2.0 license · on Arena since 26 Jan 2026
Download
Arena score1187#49 of 59 in Image edit, paid models included
Size3.9 Bparameters
4-bit download2.4 GBweights only, Q4_K_M
Max context—
Where to use it for free
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
| Arena | Score | Rank | Votes |
|---|---|---|---|
| Image | 1030 | #70 of 82 | 152K |
| Image edit | 1187 | #49 of 59 | 541K |
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
Does it fit on popular hardware?
| Hardware | GPU memory | Fits? |
|---|---|---|
| RTX 3060 12 GB | 12 GB | Fits in GPU |
| RTX 4060 Ti 16 GB | 16 GB | Fits in GPU |
| RTX 3090 | 24 GB | Fits in GPU |
| RTX 4090 | 24 GB | Fits in GPU |
| RTX 5090 | 32 GB | Fits in GPU |
| RX 7900 XTX | 24 GB | Fits in GPU |
| 2 × RTX 3090 | 48 GB | Fits in GPU |
| 4 × RTX 3090 | 96 GB | Fits in GPU |
| Mac M4 Max 128 GB | 96 GB | Fits in GPU |
| Ryzen AI Max+ 395 128 GB | 96 GB | Fits in GPU |
| 8 × H100 SXM | 640 GB | Fits in GPU |
Estimate at 4-bit, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | Total |
|---|---|
| Q3_K_M | 5.5 GB |
| Q4_K_M | 6.0 GB |
| Q5_K_M | 6.4 GB |
| Q6_K | 6.8 GB |
| Q8_0 | 7.7 GB |
| F16 | 11 GB |
Weights + text encoders and decoder (about 3 GB) + runtime. Simulate your own setup.
Image score over time
100012001400
MayJunJulAugSeptOct
flux-2-klein-4b 1030Best paid model
Arena score from 10 Apr 2026 to 7 Oct 2026.
Image edit score over time
1200130014001500
MayJunJulAugSeptOct
flux-2-klein-4b 1187Best paid model
Arena score from 10 Apr 2026 to 6 Oct 2026.
Similar free models in Image edit
- flux-2-dev 1225 · 32.2 B
- flux-2-klein-9b 1225 · 9.1 B
- flux-1-kontext-dev 1149 · 11.9 B
- qwen-image-edit-2511 1234 · 20.4 B
- qwen-image-edit 1242 · 20.4 B
- hunyuan-image-3.0 1303 · 83 B