Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Models › Jev family

Jev-Omni

Hugging Face ↗ Follow changes

akhilaaa3 Apache 2.0 out 35 days ago

12.0B parameters, text in, labels out, 256K tokens of context.

Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 5.9k · #532 of 619 tracked

Can I run it?7.2GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24
Do people use it?5.9kdownloads, 30 days#532 of 619 we track · below the median+14 likes, downloads +12% this week429 likesHugging Face2026-10-24

Worth reading

Picked by rule from 15 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 1,989 HN pts

Introducing System One Models and Jev

TypeSafe AI releases Jev, a System One Model designed for fast, structured automation decisions.

  • Jev outputs all probabilities in parallel instead of autoregressively generating by token.
  • The model never makes type errors because possible outputs and structure are defined in advance.
typesafe.ai 2026-09-15 1,989 HN pts · 520 comments 2.2k words about the Jev family family
Latest · 26 days ago

Jeeves. Reasoning improves Jev-like decision models

Jeeves is a 9B Jev-like model based on Qwen3.5-9B that reasons only when unsure, trained on public data to improve decision accuracy.

  • Jeeves v2 was trained on chains of at most 1,024 tokens, so lower caps cut most of its chains.
  • The model uses rare tokens like "<state>" and "<decide>" in the prompt, as using plain text like "State" worsened performance.
github.com 2026-09-29 242 HN pts · 95 comments 2.4k words about the Jev family family

15 best of 15 tracked

The 2 picks above, plus these 13. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. CodeJeff – Jev-compatible 0.8B decision models, trained at home, ~30 msgithub.com · 2026-09-28 · 575 HN pts
  2. CodeKev: Tiny Jev-like family of decision models built on top of Qwen3.5github.com · 2026-09-21 · 463 HN pts
  3. ArticleOllaya – Ollama for open-source, Jev-style decision modelsollaya.dev · 2026-09-25 · 618 HN pts
  4. ArticleLanguage models for text classification: From bag-of-words to Jevmagazine.sebastianraschka.com · 2026-09-29 · 213 HN pts
  5. CodeI turned Jev into a (lousy) chatbotgithub.com · 2026-09-20 · 177 HN pts
  6. ArticleDecision models like Jev don't beat LLM-as-a-judge or traditional classifiersdevelopers.redhat.com · 2026-10-02 · 165 HN pts
  7. CodeReverse-engineered Jev-like modelgithub.com · 2026-09-16 · 169 HN pts
  8. ArticleTurning GLM-5.3-Flash into a Jev-like decision modelprivatemode.ai · 2026-09-26 · 138 HN pts
  9. ArticleA single function Jev-like wrapper for LLMs, including vision modelsallanrbo.blogspot.com · 2026-09-26
  10. ArticleShow HN: JevBench, a reproducible benchmark for typed decision modelsbenchmarkheaven.com · 2026-09-22
  11. ArticleShow HN: Jevstiller – Distill Jev into a local model, with a disagreement boundjevstiller.pages.dev · 2026-09-29
  12. DiscussionOpen-sourced jev architecture last year with model,paper and datasetnews.ycombinator.com · 2026-09-17
  13. ArticleWhat Is RLCD? The Secret Behind Jevdi-zhang-llm.github.io · 2026-09-24

Where it's used

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: 4 quantized builds and 11 Spaces.

  • As a service0no API provider listed
  • On own hardware4quantized builds
  • Built on33 fine-tunes · 0 adapters · 0 merges
  • In apps11Hugging Face Spaces

Top Spaces running it: multimodalart/jev-decision-index ♥ 802 · akhilaaa3/jev-omni ♥ 26 · jmrenouard/microllm-decision-studio ♥ 1

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 16 GB card at INT4

About 7.2 GB at INT4, 14 GB at FP8, 29 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 7.2 GB of weights (estimate; KV cache and activations extra)INT47.2 GBFP8: about 14 GB of weights (estimate; KV cache and activations extra)FP814 GBBF16: about 29 GB of weights (estimate; KV cache and activations extra)BF1629 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 7.2 GB of weights (estimate; KV cache and activations extra)INT47.2 GBFP8: about 14 GB of weights (estimate; KV cache and activations extra)FP814 GBBF16: about 29 GB of weights (estimate; KV cache and activations extra)BF1629 GB

Estimate params × bytes per param × 1.2 · how we estimate

The story so far

Weights, every dated article, and repo commits on one rail.

Coverage peaked at launch and is still arriving

Teal is the weights (2026-09-20), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.

Oct2026-10-13: 1 repo commit2026-09-25: 3 repo commits2026-09-22: 7 repo commitsJeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms · 2026-09-28Introducing System One Models and Jev · 2026-09-15Kev: Tiny Jev-like family of decision models built on top of Qwen3.5 · 2026-09-21Jeeves. Reasoning improves Jev-like decision models · 2026-09-29Ollaya – Ollama for open-source, Jev-style decision models · 2026-09-25Language models for text classification: From bag-of-words to Jev · 2026-09-29I turned Jev into a (lousy) chatbot · 2026-09-20Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers · 2026-10-02Reverse-engineered Jev-like model · 2026-09-16Turning GLM-5.3-Flash into a Jev-like decision model · 2026-09-26Weights 2026-09-20 · 2026-09-20Weights 2026-09-20now
Oct2026-10-13: 1 repo commit2026-09-25: 3 repo commits2026-09-22: 7 repo commitsJeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms · 2026-09-28Introducing System One Models and Jev · 2026-09-15Kev: Tiny Jev-like family of decision models built on top of Qwen3.5 · 2026-09-21Jeeves. Reasoning improves Jev-like decision models · 2026-09-29Ollaya – Ollama for open-source, Jev-style decision models · 2026-09-25Language models for text classification: From bag-of-words to Jev · 2026-09-29I turned Jev into a (lousy) chatbot · 2026-09-20Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers · 2026-10-02Reverse-engineered Jev-like model · 2026-09-16Turning GLM-5.3-Flash into a Jev-like decision model · 2026-09-26Weights 2026-09-20 · 2026-09-20Weights 2026-09-20now

What people built on it

7 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

7 derivatives on the Hub, most of them quantized

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

4 quantized (Hugging Face model tree)3 fine-tunes (Hugging Face model tree)4 quantized3 fine-tunes
4 quantized (Hugging Face model tree)3 fine-tunes (Hugging Face model tree)4 quantized3 fine-tunes
GGUF Reza2kn/Jev-Omni-Q4_K_M-GGUF for llama.cpp, Ollama, LM Studio 6.8k downloads MLX Ruiruiz30/Jev-Omni-MLX-4bit for Apple silicon 1.5k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Benchmarks

8 rows

Benchmarks 8 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (8)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
BenchmarkValueSetting / notesReported byDate
author-reported DecisionBench Medium · 80 scenarios / 293 questions87.57% percentAccuracy¹model author2026-10-07
author-reported DecisionBench Medium · 80 scenarios / 293 questions86.01% percentMicro accuracymodel author2026-10-07
author-reported JevBench · matched 195 groups / 231 decisions86.15% percentAccuracy¹model author2026-10-07
author-reported JevBench · matched 195 groups / 231 decisions87.45% percentMicro accuracymodel author2026-10-07
author-reported MMAU · 1,000 questions63.10% percentMicro accuracymodel author2026-10-07
author-reported MVBench · 14 evaluated tasks / 2,786 questions53.10% percentAccuracy¹model author2026-10-07
author-reported MVBench · 14 evaluated tasks / 2,786 questions53.09% percentMicro accuracymodel author2026-10-07
author-reported Medium ECE0.0410 binsmodel author2026-10-07

What the card says

1 cited sentence

Summary generated, cited

Jev-Omni is a 12.0B parameter multimodal decision classifier for text, images, audio and video.[1][2]

  1. parameters human
  2. “text, images, audio and video”

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.

Use-case evidence

6 use cases

What it is good at 6 use cases

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.

Facts

19 fields

Listed in Decision models

Facts

Pipeline tagtext-classification
Librarytransformers
ArchitecturesGemma4UnifiedForConditionalGeneration
Model typegemma4_unified
Dtypebfloat16
Params by dtypeBF16: 11,959,730,224
Size bandL
MoEno
Context length262,144 (config.json max_position_embeddings)
LicenseApache 2.0 (apache-2.0)
Hub snapshot2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Gemma4UnifiedForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Gemma4UnifiedForConditionalGeneration · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed

vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Jev-Omni: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)29 GB · Single high-end GPU (<80 GB)
FP8 (1 byte/param)14 GB · Single GPU (<24 GB)
INT4 (0.5 bytes/param)7.2 GB · Single GPU (<24 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

Decision facts

catalog

Decision-model catalog curated

How it was madeLoRA + new scoring/pointer head
Lineage bucketF - fine-tune of an open model (public/synthetic data)
Lineage evidenceboard file inspection (adapter/head/weight files) + HF base_model field
Base modelgoogle/gemma-4-12B
DI 0.2.1 score40.53 (independent (DI 0.2.1 board))
ECE (board)0.1610
Median latency54.9 ms (DI board, 1x RTX PRO 6000, single process)
Hosted price (input)self-hosted/M
Sourcehttps://huggingface.co/akhilaaa3/Jev-Omni

All variants

7 variants

Lineage

Fine-tuned from google/gemma-4-12B-it Family: akhilaaa3/Jev 7 derivatives on the Hub

Base model: google/gemma-4-12B-it

quantized: 4finetune: 3

Top variants (7 shown, ranked by downloads)

Relation
Quant
7 rows
Variant Relation Quant Params Band License Author Likes Downloads
Reza2kn/Jev-Omni-Q4_K_M-GGUF quantized GGUF — — apache-2.0 Reza2kn 10 6.8k
ngquocvinh/Jev-Omni-GGUF quantized GGUF — — apache-2.0 ngquocvinh 3 3.2k
Ruiruiz30/Jev-Omni-MLX-4bit quantized MLX 12.0B L apache-2.0 Ruiruiz30 2 1.5k
ferdinandl007/glim-12b finetune — 12.0B L — ferdinandl007 0 71
ferdinandl007/jev-omni-general-head-v3 finetune — — — — ferdinandl007 0 43
ferdinandl007/jev-omni-general-head-v2 finetune — — — — ferdinandl007 0 27
ai-ecoverse/jev-omni.js quantized — — — apache-2.0 ai-ecoverse 0 0

Repository changelog

11 commits

Repository changelog 11 commits

DateCommitSHA
2026-10-13 Add decision-model tag (#2) fee89b0
2026-09-25 requirements: add torchvision and librosa 5addda8
2026-09-25 Remove the fp32 backbone/ and the duplicate unified/ copy 18043f3
2026-09-25 Make the unified bf16 checkpoint the repo root 6028e1f
2026-09-22 Model card: shorter note, small text at the end c050d51
2026-09-22 Add trademark / non-affiliation notice 60c2fae
2026-09-22 The Wall: 23-second demo film (11 cameras, voicemails, chats on one GPU) cb4a0ff
2026-09-22 unified bf16 checkpoint: base Gemma 4 12B vision/audio + fine-tuned text model, one file; verified against the reference loader c127654
2026-09-22 Simplify model card and add merged Jev-Omni Medium accuracy and calibration plots 55b53f2
2026-09-22 Update README.md 2ef0877
2026-09-22 Jev-Omni: verified public release 22d65eb

Articles and coverage

15 pieces

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.

Analysis10

Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms
github.com2026-09-28authorityHN front pageabout the Jev familyHN 575 pts · 232 comments3,771 words
Introducing System One Models and Jev
typesafe.ai2026-09-15HN front pageabout the Jev familyHN 1,989 pts · 520 comments2,189 words
TypeSafe AI releases Jev, a System One Model designed for fast, structured automation decisions. Jev achieves similar intelligence to existing LLMs while being two orders of magnitude faster and more efficient, with end-to-end response times of 70ms-500ms compared to 3 to 329 seconds for frontier models. The model costs $0.042 per million input tokens and provides 40x-200x speedups for System One shaped queries by outputting calibrated probabilities in parallel rather than generating strings autoregressively.written, reviewed, cited
  • Jev outputs all probabilities in parallel instead of autoregressively generating by token.
  • The model never makes type errors because possible outputs and structure are defined in advance.
  • Jev supports a cardinality up to 255, requiring a two-stage system for higher choices.
Kev: Tiny Jev-like family of decision models built on top of Qwen3.5
github.com2026-09-21authorityHN front pageabout the Jev familyHN 463 pts · 210 comments6,746 words
Kev is a family of small decision models built on Qwen3.5 and Qwen3.8 that you can train and run locally. The API matches TypeSafe's System One, so you can point their Python SDK at your local server. Models use a small adapter on a frozen base, except Kev-27B which ships as 51 GB of full weights. The 27B model achieves 0.851 accuracy on new sources.written, reviewed, cited
  • The Kev-27B model requires 96–128 GB of RAM on Macs, a requirement marked as expected but not measured.
  • An explicitly requested accelerator fails instead of falling back if the probe times out or crashes.
Jeeves. Reasoning improves Jev-like decision models
github.com2026-09-29authorityHN front pageabout the Jev familyHN 242 pts · 95 comments2,362 words
Jeeves is a 9B Jev-like model based on Qwen3.5-9B that reasons only when unsure, trained on public data to improve decision accuracy. It beats Kev-9B on test data it was never trained on with 0.905 vs 0.822 accuracy. Inference runs on one H100 with --precision fp8 at about 20 ms per request without thinking and a 1.2 s median with reasoning.written, reviewed, cited
  • Jeeves v2 was trained on chains of at most 1,024 tokens, so lower caps cut most of its chains.
  • The model uses rare tokens like "<state>" and "<decide>" in the prompt, as using plain text like "State" worsened performance.
  • Every training chain reaches the right answer, so answers after reasoning come out overconfident and need the larger temperature.
Ollaya – Ollama for open-source, Jev-style decision models
ollaya.dev2026-09-25HN front pageabout the Jev familyHN 618 pts · 145 comments1,022 words
Ollaya runs open decision models locally with Apache-2.0 licensing, serving as a drop-in, Jev-compatible replacement for TypeSafe's hosted decision models. It achieves 0.824 accuracy on 3,880 questions using BF16 weights, while Ollama 0.40.6 runs 5 to 8 times faster via Q8_0 GGUFs. The platform supports 25 model families across macOS, Windows, Linux, and Docker, with NVIDIA GPUs requiring driver R525 or newer.written, reviewed, cited
  • The decider model by Mapika reads answers from option-letter logits in one forward pass.
  • The gliclass model scores all options in one pass, causing CPU cost to grow with option count.
  • The kev model uses a LoRA on a Qwen3.5 base plus a pointer head that scores every option at its own span.
Language models for text classification: From bag-of-words to Jev
magazine.sebastianraschka.com2026-09-29authorityHN front pageabout the Jev familyHN 213 pts · 10 comments7,738 words
I turned Jev into a (lousy) chatbot
github.com2026-09-20authorityHN front pageabout the Jev familyHN 177 pts · 50 comments1,006 words
Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers
developers.redhat.com2026-10-02HN front pageabout the Jev familyHN 165 pts · 75 comments4,738 words
Reverse-engineered Jev-like model
github.com2026-09-16authorityHN front pageabout the Jev familyHN 169 pts · 24 comments1,019 words
Turning GLM-5.3-Flash into a Jev-like decision model
privatemode.ai2026-09-26HN front pageabout the Jev familyHN 138 pts · 59 comments2,447 words
All coverage tracked for this model (15) — append-only, nothing is ever removed
TitleSourcePublishedFirst seenSignals
Decision models like Jev don't beat LLM-as-a-judge or traditional classifiersdevelopers.redhat.com2026-10-022026-10-07hn
Show HN: Jevstiller – Distill Jev into a local model, with a disagreement boundjevstiller.pages.dev2026-09-292026-10-07hn
Jeeves. Reasoning improves Jev-like decision modelsgithub.com2026-09-292026-10-07hn
Language models for text classification: From bag-of-words to Jevmagazine.sebastianraschka.com2026-09-292026-10-07hn
Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 msgithub.com2026-09-282026-10-07hn
Turning GLM-5.3-Flash into a Jev-like decision modelprivatemode.ai2026-09-262026-10-07hn
A single function Jev-like wrapper for LLMs, including vision modelsallanrbo.blogspot.com2026-09-262026-10-07hn
Ollaya – Ollama for open-source, Jev-style decision modelsollaya.dev2026-09-252026-10-07hn
What Is RLCD? The Secret Behind Jevdi-zhang-llm.github.io2026-09-242026-10-07hn
Show HN: JevBench, a reproducible benchmark for typed decision modelsbenchmarkheaven.com2026-09-222026-10-07hn
Kev: Tiny Jev-like family of decision models built on top of Qwen3.5github.com2026-09-212026-10-07hn
I turned Jev into a (lousy) chatbotgithub.com2026-09-202026-10-07hn
Open-sourced jev architecture last year with model,paper and datasetnews.ycombinator.com2026-09-172026-10-07hn
Reverse-engineered Jev-like modelgithub.com2026-09-162026-10-07hn
Introducing System One Models and Jevtypesafe.ai2026-09-152026-10-07hn

Similar models

3 models

Similar models

  • rune-26b-a4b-GGUF · 25.8B
    same size band (L), same task (text-classification), permissive license
  • pplx-decider-v1-27b · 26.1B
    same size band (L), same task (text-classification), permissive license
  • JEV-27B · 26.9B
    same size band (L), same task (text-classification), permissive license

Sources

3 sources

Sources

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

Follow Jev-Omni

Watch this model

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.