Model comparison · embedding
granite-embedding-30m-english vs Kimi-K2.6
Symmetrical, primary-source facts with unknown values left visible. No winner is assigned without comparable measurements.
FieldAt a glance
IBM · activegranite-embedding-30m-englishVerified Aug 28, 2026
Moonshot AI · activeKimi-K2.6Verified Aug 28, 2026
Technical differences
Side-by-side facts
| Field | granite-embedding-30m-english | Kimi-K2.6 |
|---|---|---|
| Developer | IBM | Moonshot AI |
| Family | Granite Embedding 30m English | Kimi K2 6 |
| Model | granite-embedding-30m-english | Kimi-K2.6 |
| Version | granite-embedding-30m-english | Kimi-K2.6 |
| Lifecycle | active | active |
| Input modalities | Text | Text, Image |
| Output modalities | Embedding | Text |
| Context window | 514 | 262144 |
| Total parameters | 30295296 | 1026879376368 |
| Active parameters | Unknown | 32000000000 |
| License | apache-2.0 | other |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Capabilities | embeddings | chat, generation, reasoning, tools |
14 comparable fields · 10 material differences · Pair passes the primary-source comparison gate
Primary benchmark evidence
Comparable performance
No protocol-matched benchmark yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.
granite-embedding-30m-english capabilities
Input price—
Output price—
Serving providers0
Canonical IDibm-granite/granite-embedding-30m-english
Kimi-K2.6 capabilities
Input price$0.95
Output price$4.00
Serving providers1
Canonical IDmoonshotai/Kimi-K2.6
Internal comparison graph
Related comparisons
Primary evidence