Quyet-1.0-Large

Released
2026-10-03
Last refreshed
2026-10-15
Status
Researched 36d ago
Open sourceCommercial use: permittedAgentsClassificationJSON / Tool useAgent

Quyet-1.0-Large is available now for agents, classification, and json / tool use with open-source; evaluate it while provider pricing coverage matures.

Chinh Nguyen releases · 2 in the last 12 monthsChangelog →
Specifications
Family
Quyet
Released
2026-10-03
Context
8K
Parameters
31.3B
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Pricing

No tracked provider pricing is available yet.

About

Quyet-1.0-Large is the largest model in Chinh Nguyen's Quyet 1.0 family. It is a calibrated decision model built on Gemma-4-31B-it with a merged rank-16 LoRA fine-tune. Given a state (text, JSON, or a conversation) and one or more typed questions (choice, score, or true/false 'noul'), it picks one option per question and returns calibrated probabilities. It answers by reading next-token probabilities of option letters after a fixed prompt in one forward pass, with nothing generated. Per-type temperatures ship in quyet_config.json.

Providers

No active provider routes are tracked for this model yet.

Capabilities

Structured Outputs

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
71.4v1.6.0Observed 2026-10-04—
58.70.3.2Observed 2026-10-17—

Migration checks

No linked migration route is available for this model yet.

API versions

chinhnc/Quyet-1.0-LargeQuyet-1.0-Largequyet-1-0-largequyet 1.0.0