Jamba Mini 1.7
AI21
- Released
- -
- Data date
- October 3, 2026
Jamba Mini 1.7 improves source-grounded answers and instruction following, according to AI21. The provider reports a FACTS score of 0.790, compared with 0.727 for version 1.6. The hybrid model retains a 256K context window.
The weights use the Jamba Open Model License. Hugging Face requires accepting the terms and sharing contact information. AI21 documents at least two GPUs with 80 GB of memory each for BF16 deployment with up to 200K context tokens.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
FACTS (Show measurement, test conditions, and source)
- Source value
- 0.79
- Score
- 0.79
- Metric
- FACTS
- Unit
- No unit provided
- Category
- hallucination
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- AI21 Jamba Mini 1.7 model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Exact Jamba Mini 1.7 column in AI21's Grounding and instruction-following improvements table; FACTS grounding result. Benchmark-specific serving and evaluation settings are not documented.
- Context
- Vendor-reported raw score with an unspecified scale, not normalized to a percentage. Exact benchmark version, harness, sample count, sampling, reasoning setting, and run date are not supplied. Inference examples are not the benchmark protocol.
IFEcal (Show measurement, test conditions, and source)
- Source value
- 0.76
- Score
- 0.76
- Metric
- IFEcal
- Unit
- No unit provided
- Category
- instruction-following
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- AI21 Jamba Mini 1.7 model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Exact Jamba Mini 1.7 column in AI21's Grounding and instruction-following improvements table; steerability result labelled IFEcal in the source. Benchmark-specific serving and evaluation settings are not documented.
- Context
- Vendor-reported raw score with an unspecified scale. The source spells the benchmark IFEcal; no equivalence to IFEval is established. Exact version, harness, sample count, sampling, reasoning setting, and run date are not supplied. Inference examples are not the benchmark protocol.
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 6 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Unresolved | benchmark-model-identity Original wording Vectara names ai21labs/jamba-mini-1.7-2025-07. AI21 lists snapshot 2025-07 alongside API endpoint jamba-mini-1.7-2025-08. The conflicting dated model identities remain unresolved. |
| Additional source | AI21 Jamba Mini 1.7 model card (retrieved October 3, 2026) · AI21 Jamba Mini 1.7 model card · Editorial description reviewed October 4, 2026 |
| Additional source | AI21 Jamba Mini 1.7 model card (retrieved October 4, 2026) |
| Additional source | Model metadata (retrieved October 4, 2026) |
| Additional source | Model metadata (retrieved October 4, 2026) |
| Additional source | Model metadata (retrieved October 4, 2026) |