Up to date
jaredpalmer Apache 2.0 out 35 days ago
Text in, labels out.
Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 17.2k · #469 of 619 tracked
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
Kev is a family of small decision models built on Qwen3.5 and Qwen3.8 that you can train and run locally.
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: 8 quantized builds and 13 Spaces.
Top Spaces running it: multimodalart/jev-decision-index ♥ 802 · jaredpalmer/kev ♥ 93 · MahmoudGhraibeh/kev-decisions ♥ 1 · anish-shrestha/small-decision-models ♥ 1
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-09-20), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
17 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Kev-0.8B is an English decision model consisting of a LoRA adapter and a pointer head on the Qwen3.5-0.8B-Base backbone.[1] The model returns a calibrated probability distribution over supplied options in a single forward pass without generating text.[2]
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
| Pipeline tag | text-classification |
|---|---|
| Library | peft |
| MoE | no |
| Languages | en |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
| How it was made | LoRA + new scoring/pointer head |
|---|---|
| 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/Qwen3.5-0.8B-Base |
| DI 0.2.1 score | 14.60 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.0743 |
| Median latency | 41.6 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/jaredpalmer/kev-0.8b |
Base model: Qwen/Qwen3.5-0.8B-Base
quantized: 8finetune: 4merge: 2adapter: 3
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| ggml-org/Kev-0.8B-GGUF | quantized | GGUF | — | — | apache-2.0 | ggml-org | 4 | 4.9k |
| mys/kev-0.8b-GGUF | quantized | GGUF | — | — | apache-2.0 | mys | 0 | 1.3k |
| litert-community/Kev-0.8B-LiteRT | finetune | — | — | — | apache-2.0 | litert-community | 4 | 546 |
| FluidInference/kev-0.8b-coreml | quantized | — | — | — | apache-2.0 | FluidInference | 5 | 266 |
| DreamBlooms/kev-0.8b-GGUF | quantized | GGUF | — | — | apache-2.0 | DreamBlooms | 0 | 334 |
| ayan4m1/kev-0.8b-merged | merge | — | 571M | S | apache-2.0 | ayan4m1 | 0 | 231 |
| akshat-OwO/nev-0.8b | finetune | — | — | — | apache-2.0 | akshat-OwO | 1 | 32 |
| mlboydaisuke/Kev-0.8B-CoreAI | quantized | — | — | — | apache-2.0 | mlboydaisuke | 0 | 51 |
| Jacqkues/sev-0.8b | adapter | — | — | — | other | Jacqkues | 0 | 47 |
| jtatman/kev-0.8b-code-verify-v2 | adapter | — | — | — | apache-2.0 | jtatman | 0 | 44 |
| jtatman/kev-0.8b-code-verify-v1 | adapter | — | — | — | apache-2.0 | jtatman | 0 | 41 |
| LarrisX/kev-0.8b-selfteach | finetune | — | — | — | apache-2.0 | LarrisX | 0 | 23 |
| minhquan2310/dispositio | finetune | — | 144M | S | apache-2.0 | minhquan2310 | 0 | 12 |
| ai-ecoverse/kev.js | quantized | — | — | — | apache-2.0 | ai-ecoverse | 0 | 0 |
| midudev/kev-0.8b-ONNX | quantized | — | — | — | apache-2.0 | midudev | 0 | 0 |
| ai-ecoverse/kev-0.8b-vision-intent | quantized | — | — | — | openrail | ai-ecoverse | 0 | 0 |
| Starlinghq/kev-0.8b-onnx | merge | — | — | — | apache-2.0 | Starlinghq | 0 | 0 |
| Date | Commit | SHA |
|---|---|---|
| 2026-10-01 | Kev 1.0 model card (weights unchanged) | bf75a6a |
| 2026-09-24 | Kev-0.8B round 15: documents + skills in one delta | 9a45d25 |
| 2026-09-21 | calibration built in: head.pt carries the fitted temperature; KEV_TEMPERATURE=1.0 for raw logits | 54f4f87 |
| 2026-09-21 | Model card: link the Space demo | d842b1f |
| 2026-09-21 | Kev-0.8B: dates+unknowable delta (locked test 0.834 / 0.684); previous weights at tag v7-base | 2256796 |
| 2026-09-20 | Kev-0.8B: Qwen3.5-0.8B-Base, decision-v7 recipe (locked test 0.827 / 0.668) | c917ede |
| 2026-09-20 | initial commit | 931752e |
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: 2026-10-25 · HF API: 2026-10-24 21:43 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:18 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
