Individual
Plans
| Plan | Amount | Frequency | Channel(s) |
|---|---|---|---|
|
Terse Mini pre-training compute
Fund GPU/TPU compute for Terse Mini (1.5B active / 4.5B total ternary sparse transformer) pre-training on 200B tokens. All weights and training code published openly under Apache 2.0. |
USD 9,000 | One-Time | |
|
ternative v2.0 — MoE, KDA, vision support
Extend ternative to serve Terse models: MoE expert dispatch, KDA (Kimi Delta Attention) kernels, MLA with KV absorption, recurrent depth, Apple Metal backend. This makes ternative the reference inference engine for the next generation of ternary models. |
USD 15,000 | One-Time |
Payment channels
| Channel | Type | Address |
|---|---|---|
| Floss-Fund |
Other
FLOSS/fund grant |
[email protected] |
Sun, 31 May 2026 19:55:01 UTC
There was a problem with this listing's funding.json manifest. If it is not fixed, the listing will be removed from the portal.
Crawl errorerror: https://github.com/michelangeloromerochisco/ternative/blob/main/funding.json?raw=true returned 503