The story so far
Weights, every dated article, and repo commits on one rail.
21 repo commits since the weights landed
Teal is the weights (2026-09-17), grey ticks are repo commits.
Models › rlcd-modernbert family
rlcd-modernbert-151m
heman10x Apache 2.0 out 38 days ago
151M parameters, text in, labels out.
Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 27.4k · #434 of 619 tracked
Do people use it?27.4kdownloads, 30 days#434 of 619 we track · below the median+1 likes, downloads −34% this week39 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: 2 quantized builds and 8 Spaces.
- As a service0no API provider listed
- On own hardware2quantized builds
- Built on00 fine-tunes · 0 adapters · 0 merges
- In apps8Hugging Face Spaces
Top Spaces running it: multimodalart/jev-decision-index ♥ 802
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, 0.4 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
2 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
2 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.
Reference
Everything else, folded: the full tables, every source.
Benchmarks
18 rows
Benchmarks 18 rows
measured third-party leaderboard rowauthor-reported number from the model card or eval files (18)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 Adaptive ECE (10 bins) | 3.50% percent | Uncalibrated | model author | 2026-10-07 |
| author-reported Adaptive ECE (10 bins) | 3.32% percent | Calibrated | model author | 2026-10-07 |
| author-reported Equal-Width ECE (10 bins) | 3.52% percent | Uncalibrated | model author | 2026-10-07 |
| author-reported Equal-Width ECE (10 bins) | 3.35% percent | Calibrated | model author | 2026-10-07 |
| author-reported Inference Latency (p50) | 35.58 ms other | Uncalibrated | model author | 2026-10-07 |
| author-reported Inference Latency (p50) | 35.58 ms other | Calibrated | model author | 2026-10-07 |
| author-reported Inference Latency (p95) | 39.81 ms other | Uncalibrated | model author | 2026-10-07 |
| author-reported Inference Latency (p95) | 39.81 ms other | Calibrated | model author | 2026-10-07 |
| author-reported Multi-Class Brier Score | 0.08 | Uncalibrated | model author | 2026-10-07 |
| author-reported Multi-Class Brier Score | 0.08 | Calibrated | model author | 2026-10-07 |
| author-reported Negative Log-Likelihood (NLL) | 0.18 | Uncalibrated | model author | 2026-10-07 |
| author-reported Negative Log-Likelihood (NLL) | 0.18 | Calibrated | model author | 2026-10-07 |
| author-reported Out-of-Scope Abstention Precision | 89.45% percent | Uncalibrated | model author | 2026-10-07 |
| author-reported Out-of-Scope Abstention Precision | 89.45% percent | Calibrated | model author | 2026-10-07 |
| author-reported Out-of-Scope Abstention Recall | 97.50% percent | Uncalibrated | model author | 2026-10-07 |
| author-reported Out-of-Scope Abstention Recall | 97.50% percent | Calibrated | model author | 2026-10-07 |
| author-reported Top-1 Accuracy | 95.00% percent | Uncalibrated | model author | 2026-10-07 |
| author-reported Top-1 Accuracy | 95.00% percent | Calibrated | model author | 2026-10-07 |
What the card says
1 cited sentence
Use-case evidence
2 use cases
What it is good at 2 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
17 fields
Listed in Decision models
Facts
- rlcd-modernbert-151m has 151M parameters. (safetensors metadata, observed 2026-10-24)
- License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
- Created 2026-09-17, last modified 2026-09-20. (HF API, observed 2026-10-24)
| Pipeline tag | text-classification |
|---|---|
| Library | transformers |
| Architectures | GLiClassModel |
| Model type | GLiClass |
| Dtype | float32 |
| Params by dtype | F32: 151,378,176 |
| Size band | S |
| MoE | no |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 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 rlcd-modernbert-151m: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.4 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 | knowledgator/gliclass-modern-base-v2.0 |
| DI 0.2.1 score | 1.87 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.1540 |
| Median latency | 11.4 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/heman10x/rlcd-modernbert-151m |
All variants
2 variants
Lineage
Base model: knowledgator/gliclass-modern-base-v2.0
quantized: 2
Top variants (2 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| FluidInference/verdict-coreml | quantized | — | — | — | apache-2.0 | FluidInference | 0 | 75 |
| aialchemist-dev/verdict-shell-safety | quantized | — | — | — | apache-2.0 | aialchemist-dev | 0 | 0 |
Repository changelog
21 commits
Repository changelog 21 commits
| Date | Commit | SHA |
|---|---|---|
| 2026-09-20 | fix(calibration): per-cardinality temperatures fitted on held-out data | 8af2496 |
| 2026-09-17 | Upload README.md with huggingface_hub | 70fa198 |
| 2026-09-17 | Upload README.md with huggingface_hub | 382061c |
| 2026-09-17 | Upload README.md with huggingface_hub | 9271dc5 |
| 2026-09-17 | Upload train_manifest.json with huggingface_hub | 6e14342 |
| 2026-09-17 | Upload bundle_manifest.json with huggingface_hub | 4e38aef |
| 2026-09-17 | Upload calibrator.json with huggingface_hub | dd4bde5 |
| 2026-09-17 | Upload model.onnx with huggingface_hub | a243d25 |
| 2026-09-17 | Upload model_fp16.onnx with huggingface_hub | 66f10c4 |
| 2026-09-17 | Upload model.safetensors with huggingface_hub | 0dd67aa |
| 2026-09-17 | Upload README.md with huggingface_hub | 3425ef8 |
| 2026-09-17 | Upload train_manifest.json with huggingface_hub | 45b6cf9 |
| 2026-09-17 | Upload bundle_manifest.json with huggingface_hub | 62fa0ce |
| 2026-09-17 | Upload calibrator.json with huggingface_hub | 95830aa |
| 2026-09-17 | Upload config.json with huggingface_hub | 9bf545b |
| 2026-09-17 | Upload tokenizer_config.json with huggingface_hub | a7cc347 |
| 2026-09-17 | Upload tokenizer.json with huggingface_hub | 2e742c4 |
| 2026-09-17 | Upload model.onnx with huggingface_hub | a0ce803 |
| 2026-09-17 | Upload model_fp16.onnx with huggingface_hub | e9cbb94 |
| 2026-09-17 | Upload model.safetensors with huggingface_hub | d622d12 |
| 2026-09-17 | initial commit | f25ce5b |
Similar models
3 models
Similar models
- Lumma-fev-0.1b · 154M same size band (S), same task (text-classification), permissive license
- Julia-1 · 144M 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 21:44 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:19 UTC · Last verified 2026-10-25
Follow rlcd-modernbert-151m
Watch this model
- /feeds/models/heman10x--rlcd-modernbert-151m.xml(RSS 2.0) · every change to rlcd-modernbert-151m
- /feeds/families/heman10x--rlcd-modernbert.xml(RSS 2.0) · every change across the rlcd-modernbert family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.