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…
![[HYU_NLP] EVA Team logo](/media/mh-logo-hyu-nlp-eval-558e075b88.webp){kind=logo}
Open-weight model · Text generation
qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003
by [HYU_NLP] EVA Team HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003
qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003 is an open-weight model for text generation from [HYU_NLP] EVA Team, released under Apache License 2.0. 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 329 downloads a month.
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.
Parameters4B
Context262,144
Weights25.7 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads329
Runs On
What it takes to serve qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003 (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 7, 2026.
Model Card
By [HYU_NLP] EVA Team, published under apache-2.0, revision ab078c7e03e6.
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…
Read [HYU_NLP] EVA Team's full model card
OnlineRubrics RaR-Medicine: step 3, seed 11
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).
original_checkpoint/ 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 precision/serialization differs.
Base model revision: cdbee75f17c01a7cc42f958dc650907174af0554 Original actor tree SHA256: c2dd930f30c54f9b962b0cc17669871a89d1e71f2abcb748cf38fe115a53eddb
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
- HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003
- Publisher
- [HYU_NLP] EVA Team
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 4B parameters
- Languages
- rar-medicine
- Revision
- ab078c7e03e6ed98aaadf939d58c5a5a8c9fcddf
- First published
- 2026-09-09
- Last updated
- 2026-09-23
Files and Weights
17 files, 25.7 GB in total. The weights are 2 files totalling 25.7 GB in pt, safetensors.
Weights2 files · 25.7 GB
Configuration6 files · 6.3 KB
Tokenizer4 files · 22.8 MB
Documentation2 files · 12.4 KB
Other2 files · 5.3 KB
Repository1 file · 1.7 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 8.0 GB | 611f3d77ab8e |
| original_checkpoint/actor/model_world_size_1_rank_0.pt | Weights | 17.6 GB | 71ce7cf84fbf |
| archive_manifest.json | Configuration | 2.6 KB | — |
| config.json | Configuration | 1.6 KB | — |
| generation_config.json | Configuration | 213 B | — |
| original_checkpoint/actor/fsdp_config.json | Configuration | 46 B | — |
| original_checkpoint/actor/huggingface/config.json | Configuration | 1.6 KB | — |
| original_checkpoint/actor/huggingface/generation_config.json | Configuration | 213 B | — |
| LICENSE | Documentation | 11.3 KB | — |
| README.md | Documentation | 1.1 KB | — |
| chat_template.jinja | Other | 2.6 KB | — |
| original_checkpoint/actor/huggingface/chat_template.jinja | Other | 2.6 KB | — |
| .gitattributes | Repository | 1.7 KB | — |
| original_checkpoint/actor/huggingface/tokenizer.json | Tokenizer | 11.4 MB | be75606093db |
| original_checkpoint/actor/huggingface/tokenizer_config.json | Tokenizer | 694 B | — |
| tokenizer.json | Tokenizer | 11.4 MB | be75606093db |
| tokenizer_config.json | Tokenizer | 694 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 25.7 GB
Download from [HYU_NLP] EVA Team
Released by [HYU_NLP] EVA Team through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3-4B-Instruct-2507
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 25.7 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 qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003
How much GPU memory does qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003 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 qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003 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 qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003 commercially?
Yes. qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is qwen3-4b-rar-medicine-onlinerubrics-seed11-step-003'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 is an autonomous risk scoring, compliance verification, and dispute adjudication model fine-tuned on top of Qwen/Qwen3-4B-Instruct-2507. It is engineered for both ends of a stablecoin payment's operational lifecycle: Autonomous on-chain agents can hallucinate payment transfers, sign malformed calldata, or trigger catastrophic transactions during market depegs. The deterministic pre-filter and policy firewall is available directly as a verified Action Provider for the Coinbase AgentKit framework: Register RiskGateActionProvider as the payment provider on your AgentKit instance. It checks chain support, policies, and peg deviations, executing safe ERC-20 transfers only after…
A fine-tuned decision engine based on Qwen/Qwen3-4B, submitted to the Decision Index v0.2.1 leaderboard. Decision Index: 40.1 (raw 54.18) — above Tev1-4B (29.2), within 6 points of Scion v4 9B (45.9). Per-area breakdown against all 4B submissions on Decision Index 0.2.1. kas-4b leads the 4B tier on: - Knowledge & Reasoning (39.5) — highest of all 4B models; higher LoRA rank (r64) likely helps on harder reasoning tasks - Arts & Human Taste (37.7) — highest of all 4B models by a wide margin - Language Understanding (35.2) — 13–25 points behind ezjev and Nox; language-heavy fine-tuning data favors those models - Tools & Automation (49.0) — behind ezjev (69.9) and Nox (60.1) Profile: the most…