IdeaLens-Qwen3.5-9B is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o scores.jsonl…
Open-weight model · Text classification
IdeaLens-Qwen3.5-9B-PerItem
by Rishanth Rajendhran rishanthrajendhran/IdeaLens-Qwen3.5-9B-PerItem
IdeaLens-Qwen3.5-9B-PerItem is an open-weight model for text classification from Rishanth Rajendhran, released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0. It has 7.9B parameters and a 262,144-token context. At 16-bit it needs about 19 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 9 downloads a month.
IdeaLens-Qwen3.5-9B-PerItem is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote.
Parameters7.9B
Context262,144
Weights15.9 GB
Licensecc-by-nc-sa-4.0
AccessOpen weights
Monthly Downloads9
Runs On
What it takes to serve IdeaLens-Qwen3.5-9B-PerItem (7.9B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 15.9 GB | 19.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.9 GB | 9.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.0 GB | 4.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 6, 2026.
IdeaLens-Qwen3.5-9B-PerItem on every accelerator the SAVRN Index prices, at every precision
Model Card
IdeaLens-Qwen3.5-9B-PerItem is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o…
Excerpt from the card by Rishanth Rajendhran, licensed cc-by-nc-sa-4.0.
Configuration
- Architecture
- Qwen3_5TextForSequenceClassification
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 12,288
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5_text
Identity and Version
- Repository
- rishanthrajendhran/IdeaLens-Qwen3.5-9B-PerItem
- Publisher
- Rishanth Rajendhran
- Task
- Text classification
- Modality
- Text
- Library
- transformers
- Parameters
- 7.9B parameters
- Languages
- en
- Revision
- 5a8f276433d77dd7c50bfa3ab8c4b78991446ed6
- First published
- 2026-08-26
- Last updated
- 2026-10-06
Files and Weights
9 files, 15.9 GB in total. The weights are 1 file totalling 15.9 GB in safetensors.
Weights1 file · 15.9 GB
Configuration2 files · 8.2 KB
Tokenizer2 files · 20.0 MB
Documentation2 files · 25.7 KB
Other1 file · 7.8 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 15.9 GB | 8820aead1495 |
| config.json | Configuration | 2.2 KB | — |
| thresholds.json | Configuration | 6.0 KB | — |
| LICENSE | Documentation | 20.9 KB | — |
| README.md | Documentation | 4.8 KB | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- cc-by-nc-sa-4.0
- Access
- Open weights, no gate
- Download size
- 15.9 GB
Download from Rishanth Rajendhran
Released by Rishanth Rajendhran through its official repository on Hugging Face.
Built From
- Derived from Qwen/Qwen3.5-9B
- Described by arXiv:2610.06778
- Trained on (disclosed) rishanthrajendhran/WildOutlines
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 15.9 GB |
| 16-bit | 15.9 GB |
| 8-bit | 7.9 GB |
| 4-bit | 4.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About IdeaLens-Qwen3.5-9B-PerItem
How much GPU memory does IdeaLens-Qwen3.5-9B-PerItem need?
About 19 GB at 16-bit and 4.8 GB at 4-bit: the weights (7.9B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run IdeaLens-Qwen3.5-9B-PerItem on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use IdeaLens-Qwen3.5-9B-PerItem commercially?
Not without separate permission. IdeaLens-Qwen3.5-9B-PerItem is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0. CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission.
What is IdeaLens-Qwen3.5-9B-PerItem's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.
Similar Models
Jev-LCT-Qwen3-8B is the flagship enterprise-grade decision engine of the Jev-LCT family. Combining Qwen3-8B's extensive foundational capabilities with Looped Calibration and adaptive early exit, it provides frontier generative reasoning capabilities with deterministic sub-100ms decision latency. - 85.0% 科学推理 + 70.0% MMLU：媲美中大型生成模型的复杂逻辑推理能力，但单次推断控制在 89.2 ms 内。 - 企业级智能体中枢：支持高风险场景的“选择性预测（Selective Prediction）”，在 80% 覆盖率下实现近乎零差错审核。 - 全量独立权重：开箱即用，支持多 GPU 分片或单张 24GB 显卡（RTX 3090 / 4090）bfloat16 全速推断。 Apache License 2.0. Full repository at GitHub.
EXL3 4.00 bpw conversion of perplexity-ai/pplx-decider-v1-27b. pplx-decider-v1-27b does not use the normal LM-head token-generation path for its final answer. It produces a hidden state and applies the model's custom readout.safetensors decision head to obtain option probabilities. The repository therefore includes pplxdeciderexl3.py, which registers the model architecture and performs the custom decision readout. This model is not recommended for standard TabbyAPI usage. A local smoke test with TabbyAPI and ExLlamaV3 1.5.2 failed during startup with: More importantly, simply registering the architecture is not sufficient for normal /v1/chat/completions behavior: TabbyAPI's standard…
100x faster than generative LLMs • Runs on laptops & cloud CPUs • Global #1 on JevBench When you ask ChatGPT or Claude a question, it generates words one token at a time, like a person typing out an essay. That takes 2 to 5 seconds and burns expensive GPU compute. That is great for writing a story, but it is painfully slow and expensive for simple decisions: - "Did the AI make up this answer, or is it actually in the PDF?" - "Should this customer's message go to billing, shipping, or technical support?" - "Does the revenue bar chart support this financial claim?" - "Did the student get the math problem right according to the answer key?" Psychologist Daniel Kahneman described human thinking…
100x faster than generative LLMs • Runs on laptops & cloud CPUs • Global #1 on JevBench When you ask ChatGPT or Claude a question, it generates words one token at a time, like a person typing out an essay. That takes 2 to 5 seconds and burns expensive GPU compute. That is great for writing a story, but it is painfully slow and expensive for simple decisions: - "Did the AI make up this answer, or is it actually in the PDF?" - "Should this customer's message go to billing, shipping, or technical support?" - "Does the revenue bar chart support this financial claim?" - "Did the student get the math problem right according to the answer key?" Psychologist Daniel Kahneman described human thinking…
Experimental open-weights judgment model by Kitani OpenJudgement is unfinished. We're releasing this checkpoint for people to experiment with, inspect, and build on. It still needs work on judgment quality, calibration, and inference efficiency. It is not as good as Jev overall in our internal task comparisons. It does show a meaningful improvement over untouched Qwen on our recorded validation comparison: 75.4% versus 64.2% annotation agreement. That is a result on a particular evaluation set, not a claim that we beat the base model on every task. There are questions it handles well and questions it confidently gets wrong. Please judge the preview by your own examples rather than assuming…