The story so far
Weights, every dated article, and repo commits on one rail.
7 repo commits since the weights landed
Teal is the weights (2026-09-23), grey ticks are repo commits.
Julia-1
SupersonicLabs Apache 2.0 out 32 days ago
144M parameters, text in, labels out.
Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 6.2k · #529 of 619 tracked
Changed this week: 1 new quantized build on the Hub (6 in all).2026-10-24
Do people use it?6.2kdownloads, 30 days#529 of 619 we track · below the median+7 likes, downloads +9% this week489 likesHugging Face2026-10-24
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: 6 quantized builds and 9 Spaces.
- As a service0no API provider listed
- On own hardware6quantized builds
- Built on88 fine-tunes · 0 adapters · 0 merges
- In apps9Hugging Face Spaces
Top Spaces running it: multimodalart/jev-decision-index ♥ 802 · SupersonicLabs/julia-1-decision-demo ♥ 12 · shreyask/open-jev-demo ♥ 2 · shreyask/open-jev-julia-demo ♥ 1
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 0.1 GB at INT4, 0.2 GB at FP8, 0.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
What people built on it
14 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
14 derivatives on the Hub, most of them fine-tunes
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
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.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported AG News · 4 labels | 94.00% percent | — | model author | 2026-10-07 |
| author-reported Banking77 · Classify and make typed decisions | 64.00% percent | — | model author | 2026-10-07 |
| author-reported DAIR Emotion · 6 labels | 86.00% percent | — | model author | 2026-10-07 |
| author-reported MASSIVE scenario classification | 71.50% percent | All 52 locales | model author | 2026-10-07 |
| author-reported MASSIVE scenario classification | 86.25% percent | Portuguese · pt-PT | model author | 2026-10-07 |
| author-reported MASSIVE scenario classification | 86.75% percent | English · en-US | model author | 2026-10-07 |
| author-reported Typed accuracy: Choice | 71.33% percent | — | model author | 2026-10-07 |
| author-reported Typed decisions | 73.15% percent | — | model author | 2026-10-07 |
What the card says
1 cited sentence
Summary generated, cited
It processes a state, a question, and possible answers to produce a single decision.[1]
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
3 use cases
What it is good at 3 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.
- Classify and make typed decisionsauthor-reportedAuthor reports Banking77 pilot · 72 labels 64.00%decision-model estimate p=1.00tag: decision-model+2 more
- Work across languagesstructuraldecision-model estimate p=0.93tag: multilingual
- Run on a laptop or phonestructuraldecision-model estimate p=0.89fits: edge
Facts
13 fields
Listed in Decision models
Facts
- Julia-1 has 144M parameters. (safetensors metadata, observed 2026-10-24)
- License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
- Created 2026-09-23, last modified 2026-09-26. (HF API, observed 2026-10-24)
| Pipeline tag | text-classification |
|---|---|
| Library | pytorch |
| Params by dtype | F32: 144,292,870 |
| Size band | S |
| MoE | no |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for Julia-1: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.3 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.2 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.1 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Decision facts
catalog
Decision-model catalog curated
| How it was made | full fine-tune (whole weights published) |
|---|---|
| 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 | jhu-clsp/mmBERT-small |
| DI 0.2.1 score | 5.54 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.4197 |
| Median latency | 5.8 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/SupersonicLabs/Julia-1 |
All variants
14 variants
Lineage
Base model: jhu-clsp/mmBERT-small
quantized: 6finetune: 8
Top variants (14 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| ggml-org/Julia-1-GGUF | quantized | GGUF | — | — | apache-2.0 | ggml-org | 21 | 10.9k |
| SupersonicLabs/Julia-1-ONNX | quantized | — | — | — | apache-2.0 | SupersonicLabs | 42 | 0 |
| andrelucas/Julia-1-GGUF | quantized | GGUF | — | — | apache-2.0 | andrelucas | 0 | 504 |
| zainmerchan/Julia-1-MLX | quantized | MLX | 144M | S | apache-2.0 | zainmerchan | 5 | 0 |
| litert-community/Julia-1-LiteRT | finetune | — | — | — | apache-2.0 | litert-community | 1 | 140 |
| mlboydaisuke/Julia-1-CoreAI | finetune | — | — | — | apache-2.0 | mlboydaisuke | 1 | 24 |
| precisionailabs/julia-routing-strix-halo-multilingual | finetune | — | 144M | S | apache-2.0 | precisionailabs | 1 | 0 |
| jfrog-boost/Julia-1-GGUF | quantized | GGUF | — | — | apache-2.0 | jfrog-boost | 0 | 50 |
| SHSLab/Qyvos | finetune | — | 144M | S | — | SHSLab | 0 | 37 |
| precisionailabs/julia-routing-strix-halo | finetune | — | 144M | S | apache-2.0 | precisionailabs | 0 | 0 |
| ampixa/barga | finetune | — | — | — | apache-2.0 | ampixa | 0 | 0 |
| niko0xdev/julia-1-zorch | finetune | — | 144M | S | apache-2.0 | niko0xdev | 0 | 0 |
| niko0xdev/julia-1-zorch-triage | finetune | — | 144M | S | apache-2.0 | niko0xdev | 0 | 0 |
| japskua/julia-1-int8-onnx | quantized | int8 | — | — | apache-2.0 | japskua | 0 | 0 |
Repository changelog
7 commits
Repository changelog 7 commits
| Date | Commit | SHA |
|---|---|---|
| 2026-09-26 | Preserve Boolean criteria and add pinned accuracy reproduction | a85b127 |
| 2026-09-26 | Add root manifest for Hub download statistics | 7a169d1 |
| 2026-09-26 | Unify named typed-question API with Dumont while retaining list requests | 7ade0af |
| 2026-09-26 | Enable native 8192-token Julia-1 inference context | 81b0424 |
| 2026-09-25 | Readme update | 111207e |
| 2026-09-25 | Update README.md | 0949494 |
| 2026-09-25 | Publish Julia 1 model and Python runtime | 5278d6b |
Similar models
3 models
Similar models
- rlcd-modernbert-151m · 151M same size band (S), same task (text-classification), permissive license
- Lumma-fev-0.1b · 154M same size band (S), same task (text-classification), permissive license
- sokudan-ja-310m · 315M same size band (S), 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 Julia-1
Watch this model
- /feeds/models/SupersonicLabs--Julia-1.xml(RSS 2.0) · every change to Julia-1
- /feeds/families/SupersonicLabs--Julia-1.xml(RSS 2.0) · every change across the Julia-1 family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.