Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…
CHILLGuard-4B is an open-weight model for text generation from Wenbo Yu, released under Creative Commons Attribution-NonCommercial 4.0. It has 4B parameters and a 262,144-token context. At 16-bit it needs about 9.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 5 downloads a month.
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment (Findings of EMNLP 2026) CHILLGuard-4B is a fine-grained Chinese LLM content-safety guardrail classifier fine-tuned from…
Parameters4B
Context262,144
Weights8.0 GB
Licensecc-by-nc-4.0
AccessOpen weights
Monthly Downloads5
Runs On
What it takes to serve CHILLGuard-4B (4B 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 | 8.0 GB | 9.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.0 GB | 4.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.0 GB | 2.4 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 24, 2026.
CHILLGuard-4B on every accelerator the SAVRN Index prices, at every precision
Model Card
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment (Findings of EMNLP 2026) CHILLGuard-4B is a fine-grained Chinese LLM content-safety guardrail classifier fine-tuned from Qwen3-4B. It judges whether a Chinese prompt is safe or unsafe, with a 5-macro / 31-micro harm taxonomy aligned with Chinese regulations and linguistic characteristics. - Achieves state-of-the-art performance on Chinese content-safety benchmarks (see the paper for detailed evaluation results). The model is trained with the generator–classifier collaborative training framework via Model-aware Direct Preference Optimization (MDPO) described in…
Excerpt from the card by Wenbo Yu, licensed cc-by-nc-4.0.
Configuration
- Architecture
- Qwen3ForCausalLM
- Context length (tokens)
- 262,144
- Layers
- 36
- Hidden size
- 2,560
- Feed-forward size
- 9,728
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 151,936
- Model type
- qwen3
Identity and Version
- Repository
- cswbyu/CHILLGuard-4B
- Publisher
- Wenbo Yu
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 4B parameters
- Languages
- Not stated by the source
- Revision
- 0cd94f94b3717788d86ac57c40aaad95859614d1
- First published
- 2026-10-05
- Last updated
- 2026-10-19
Files and Weights
8 files, 8.1 GB in total. The weights are 1 file totalling 8.0 GB in safetensors.
Weights1 file · 8.0 GB
Configuration2 files · 1.8 KB
Tokenizer2 files · 11.4 MB
Documentation1 file · 3.9 KB
Other1 file · 2.6 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 8.0 GB | 348edce9419d |
| config.json | Configuration | 1.6 KB | — |
| generation_config.json | Configuration | 212 B | — |
| README.md | Documentation | 3.9 KB | — |
| chat_template.jinja | Other | 2.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | be75606093db |
| tokenizer_config.json | Tokenizer | 665 B | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 8.0 GB
Download from Wenbo Yu
Released by Wenbo Yu through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3-4B
- Described by arXiv:2606.15396
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 8.0 GB |
| 16-bit | 8.0 GB |
| 8-bit | 4.0 GB |
| 4-bit | 2.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About CHILLGuard-4B
How much GPU memory does CHILLGuard-4B need?
About 9.7 GB at 16-bit and 2.4 GB at 4-bit: the weights (4B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run CHILLGuard-4B 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 CHILLGuard-4B commercially?
Not without separate permission. CHILLGuard-4B is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
What is CHILLGuard-4B's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.
Similar Models
We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements: - Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. - Substantial gains in long-tail knowledge coverage across multiple languages. - Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation. - Enhanced capabilities in 256K long-context understanding. Qwen3-4B-Instruct-2507 has the following features: NOTE: This model supports only non-thinking…
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: Qwen3-4B-Base has the following features: For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation. The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers. With transformers<4.51.0, you will…
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: Qwen3-4B-Base has the following features: For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation. The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers. With transformers<4.51.0, you will…
SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers approve, hold or reject with reason codes. It is a 4B model, fine-tuned from Qwen/Qwen3-4B-Instruct-2507, that runs on a laptop. It reads three things: your policy, the payment request exactly as received (treated as untrusted), and the results of your own verification tools (signature checks, attestations, sanctions screening). It is a decision-support layer that sits behind deterministic checks, not a standalone security control. It also proposes settlement-aware remedies for payment disputes. All 4 unsafe approvals were prompt injections; the companion SDK's deterministic claims check holds all 4…
![[HYU_NLP] EVA Team logo](/media/mh-logo-hyu-nlp-eval-558e075b88.webp){kind=logo}
Intermediate policy from dynamic OnlineRubrics-Every GRPO training. Distinct from static-rubric GRPO. Base model: Qwen/Qwen3-4B-Instruct-2507; thinking disabled. This checkpoint is a policy state used by the Phase-1 audit. No downstream medical capability or safety claim is made. Research use only; not validated for clinical decision-making. Root files are the veRL-exported Hugging Face inference model (BF16). originalcheckpoint/ preserves the exact original FSDP parameter checkpoint and tokenizer/configuration files. Optimizer state, training data, responses, rubrics, infrastructure configuration, and credentials are not included. The original is retained because export…