Model Detail
Qwen3-4B
—Qwen3-4B is a large language model with 4B parameters released by Qwen. The model is registered under the text-generation pipeline tag on Hugging Face.
Qwen3-4B is priced at $0.08/M input tokens and $0.24/M output tokens. Operationally the model offers a 33K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.
Qwen3-4B ships with 4B parameters.
Qwen3-4B is best fit for general-purpose chat and instruction-following workloads, and high-volume batch jobs where per-call cost dominates the budget. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
QU-NLP at ArchEHR-QA 2026: Two-Stage QLoRA Fine-Tuning of Qwen3-4B for Patient-Oriented Clinical Question Answering and Evidence Sentence Alignment
arXiv:2604.14175v1 Announce Type: new Abstract: We present a unified system addressing both Subtask 3 (answer generation) and Subtask 4 (evidence sentence alignment) of the ArchEHR-QA Shared Task. For Subtask 3, we apply two-stage Quantised Low-Rank Adaptation (QLoRA) to Qwen3-4B loaded in 4-bit NF4
LinguIUTics at PsyDefDetect: Iterative Imbalance-Aware Fine-tuning of Qwen3-8B for Psychological Defense Mechanism Classification
arXiv:2606.00647v1 Announce Type: cross Abstract: Detecting psychological defense mechanisms in conversational text remains a challenging clinical NLP problem. For the PsyDefDetect 2026 shared task (nine-class utterance classification evaluated via macro F1), our team LinguIUTics achieves a macro F1
Procedural-skill SFT across capacity tiers: A W-Shaped pre-SFT Trajectory and Regime-Asymmetric Mechanism on 0.8B-4B Qwen3.5 Models
arXiv:2605.11907v2 Announce Type: replace Abstract: We measure procedural-skill SFT contribution across three Qwen3.5 dense scales (0.8B, 2B, 4B) on a 200-task / 40-skill holdout, with Claude Haiku 4.5 as a frontier reference. The corpus is 353 rows of (task + procedural-skill block, Opus chain-of-t
Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
arXiv:2605.07141v1 Announce Type: cross Abstract: Open-world referring segmentation requires grounding unconstrained language expressions to precise pixel-level regions. Existing multimodal large language models (MLLMs) exhibit strong open-world visual grounding, but their outputs remain limited to
Qwen3.5-Omni Technical Report
arXiv:2604.15804v2 Announce Type: replace Abstract: In this work, we present Qwen3.5-Omni, the latest advancement in the Qwen-Omni model family. Representing a significant evolution over its predecessor, Qwen3.5-Omni scales to hundreds of billions of parameters and supports a 256k context length. By
AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
arXiv:2601.17261v4 Announce Type: replace Abstract: Zeroth-Order (ZO) optimization has emerged as a promising solution for fine-tuning LLMs under strict memory constraints, as it avoids the prohibitive memory cost of storing activations for backpropagation. However, existing ZO methods typically emp
