A 21B reasoning model, trained with RLOO and released under Apache 2.0. This is the first open weights release by Reka AI but it went under due to the release of Gemma shortly after. However, the model is really capable, especially for its size. In our testing, it came close to the performance of 32B models, such as the R1-distill of Qwen and QwQ 32B.
Specs
Params21B
LicenseApache-2.0
Similarity · VAIL
VAIL Fingerprint
0324:0528:0732:09dd:0ca0:1691:27e6:5d64
Explore other models with behavioral similarity to Reka Flash 3.
Capability · Artificial Analysis
AA Index
3.7
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
442
last 30d
21.1K
all time
HF Likes
388
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Related Models
