Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open+14%—$0 / —Memory (4-bit): 5.5 GB → 16 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+14%—$0 / —Memory (4-bit): 5.5 GB → 16 GBModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+14%—$0 / —Memory (4-bit): 5.5 GB → 16 GBAll baselabs models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
in Decision modelsFAQ
How much does elephant-1 (9B) cost?›
$0 per 1M input tokens and — per 1M output tokens (cheapest host: OpenRouter).
Is elephant-1 (9B) free to use?›
Yes, there is a free API option.
How good is elephant-1 (9B), and what is it best at?›
#17 of 99 in Decision models.
Is elephant-1 (9B) better than KnowLine 35B-A3B Gen1?›
On Community Decision Index 0.4.1, elephant-1 (9B) scores 60.3 vs 61.2 — about the same.
How can I use elephant-1 (9B)?›
Through the baselabs API.
What is the context window of elephant-1 (9B)?›
16K tokens.
When was elephant-1 (9B) released? Is there a newer version?›
Released 2026-10-19. It is the current version in its line.
Is elephant-1 (9B) open source?›
Yes, the weights are open (MIT licence).
Can I run elephant-1 (9B) locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can elephant-1 (9B) read images?›
No, it accepts text only.
What is elephant-1 (9B)?›
elephant-1 (9B) is an open-weights language model from baselabs, released Oct 2026.
What are the best alternatives to elephant-1 (9B)?›
mammoth-1 (27B) (better), Decider Flash v1.2 (open weights).