Up to date
bespokelabs Apache 2.0 out 33 days ago
Verified 2026-10-26 07:27 UTC Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 836 · #597 of 619 tracked
Picked by rule from 3 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Bespoke is a free, open-source modular synthesizer licensed under GPLv3 with releases for Mac, Windows, and Linux.
The 2 picks above, plus these 1. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 7 Spaces.
Top Spaces running it: multimodalart/jev-decision-index ♥ 802
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-09-23), amber triangles are 3 dated articles (each links to it), grey ticks are repo commits.
Everything else, folded: the full tables, every source.
Bespoke-Nimble-9B-v2 is a PEFT LoRA adapter for text-based, schema-conditioned decisions based on the Qwen/Qwen3.5-9B model.[1][2] The model scores answer-token logits to provide boolean judgments, categorical choices, and ordinal scores under an Apache 2.0 license.[3][4] It supports up to 255 choices per field within an 8,192-token context limit.[5][6]
Generated 2026-10-07 15:18 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in Decision models
| Library | peft |
|---|---|
| MoE | no |
| Languages | en |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-26 |
| How it was made | LoRA/adapter fine-tune |
|---|---|
| Lineage bucket | F - fine-tune of an open model (public/synthetic data) |
| Lineage evidence | board file inspection (adapter/head/weight files) + HF base_model field |
| Base model | Qwen/Qwen3.5-9B-Base |
| DI 0.2.1 score | 39.57 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.0240 |
| Median latency | 77.3 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/bespokelabs/Bespoke-Nimble-9B-v2 |
Base model: Qwen/Qwen3.5-9B
| Date | Commit | SHA |
|---|---|---|
| 2026-09-23 | Support up to 255 choices in v2 inference without changing weights | 4b8c04d |
| 2026-09-23 | Document automatic v2 temperature in the GitHub loaders | e1f8311 |
| 2026-09-23 | Require explicit opt-in for raw v2 probabilities | aec13f1 |
| 2026-09-23 | Apply transferred GitHub probability temperature to v2 scoring | 84c365a |
| 2026-09-23 | Update README.md | 01ebf0a |
| 2026-09-23 | Upload verified 4926-example Bespoke-Nimble-9B-v2 LoRA checkpoint | a3ca9ca |
| 2026-09-23 | initial commit | 9388849 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
Hub snapshot: 2026-10-26 · HF API: 2026-10-26 07:25 UTC · Providers: 2026-10-26 07:26 UTC · Articles: 2026-10-26 07:27 UTC · Summary: 2026-10-07 15:18 UTC · Last verified 2026-10-26 07:27 UTC
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
