whatmodel.sh / image / FLUX.2 [klein] 4B
FLUX.2 [klein] 4B
↗ share
+ contribute
FLUX.2 [klein] 4B is an open-weights image model from Black Forest Labs, released January 2026. Its published size is 4B parameters. Licence: apache-2.0.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of FLUX.2 [klein] 4B, out of 197 with a score, then more from Black Forest Labs.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 95 |  UniPic 3 | 52±3 | comparison only | ||
| 96 |  Imagen 3 (imagen-3.0-generate-002) | 52±2 | comparison only | ||
| 97 | FLUX.2 [klein] 4B | 52±2 | api $0.0011/image +local | ||
| 98 |  P-Image | 51±2 | api $0.0050/image | ||
| 99 |  Photon | 51±2 | api $0.019/image | ||
| more from Black Forest Labs | |||||
| 32 | FLUX.2 [max] | 64±1 | api $0.070/image | ||
| 36 | FLUX.2 [pro] | 63±2 | api $0.030/image | ||
| 37 | FLUX.2 [flex] | 62±2 | api $0.050/image | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #68 of 126 · 75% of its score · 3 tests
Trails FLUX.1 Kontext [pro], Photon, P-Image here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1030.0 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 12/75 | 45% |
| QC-T2I-Bench (English, HCQ total) | 84.3% ✎ | ▄····▄█▄▄█▄█ beats 3/10 | 18% |
| UltraText Bench (Composite, bilingual dense text rendering) | 19.6% ✎ | ▁▃▂█▃▁▂▃·▁·▁ beats 2/22 | 11% |
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #42 of 62 * · 24% of its score · 2 tests
Beats GPT Image 1 Mini, FLUX.1 Kontext [max], Qwen-Image here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image edit | 1187.5 ✎ | ▂▁▁▂▆▇█▄▆▅▁▂ beats 10/53 | 17% |
| GEditBench v2 (overall Elo) | 1031.0 ✎ | ▃▂····▂█▃▃▂▃ beats 9/14 | 6.8% |
$ where to run it
Through an API
api · Cloudflare · $0.0011/image · developers.cloudflare.com ↗ · price sourceCloudflare Workers AI; 4 output tiles × USD0.000287/output tile; zero input-image tiles. Workers plan fee excluded; published USD equivalent is rounded, service bills Neurons. Product: Workers AI text-to-image. API model: @cf/black-forest-labs/flux-2-klein-4b. Settings: width=1024, height=1024, input images=0, output tiles=4. Price basis: derived fixed-setting output cost using published rounded USD rates. Additional/excluded charges: Workers Paid plan base fee, input images and usage beyond this setting. Currency: USD.
Other ways to run it
version
- Run it as published · needs ~2.9 GB, Mac only · from github.com/mflux-community
uvx --from mflux mflux-generate-flux2 --model flux2-klein-4b --prompt "a cat holding a sign" --steps 4 -q 4
Official weights and documentation: huggingface.co/black-forest-labs ↗
$ how the score was worked out · LMArena leaderboard dataset 63%, QC-T2I-Bench: Scalable Questi… 18%, UltraText Bench: A Comprehens… 11% and 1 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 2 | 63% |
 QC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing) | 1 | 18% |
| UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1) | 1 | 11% |
| GEditBench v2: A Human-Aligned Benchmark for General Image Editing | 1 | 7% |
| prior · pull toward the middle | 1% | |
| weighted average | = 51.5 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json