What are the hardware requirements for QiMing Weaver?

QiMing Weaver requires approximately 29.2 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed QiMing Weaver and how large is it?

QiMing Weaver is developed by aifeifei798, a model with 14b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate QiMing Weaver?

QiMing Weaver is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

QiMing Weaver by aifeifei798 — VRAM 29.2GB, 40K context

Name: QiMing Weaver
Author: aifeifei798

QiMing Weaver is an open-source language model by aifeifei798. Features: 14b LLM, VRAM: 29.2GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.2.

Model Card on HF 🤗: https://huggingface.co/aifeifei798/QiMing-Weaver

QiMing Weaver Parameters and Internals

LLM Name	QiMing Weaver
Repository 🤗	https://huggingface.co/aifeifei798/QiMing-Weaver
Base Model(s)	Qwen3 14B Qwen/Qwen3-14B
Model Size	14b
Required VRAM	29.2 GB
Updated	2026-07-28
Maintainer	aifeifei798
Model Type	qwen3
Model Files	1.6 GB: 1-of-32 1.0 GB: 2-of-32 0.8 GB: 3-of-32 1.0 GB: 4-of-32 0.8 GB: 5-of-32 0.8 GB: 6-of-32 1.0 GB: 7-of-32 0.8 GB: 8-of-32 0.8 GB: 9-of-32 1.0 GB: 10-of-32 0.8 GB: 11-of-32 0.8 GB: 12-of-32 1.0 GB: 13-of-32 0.8 GB: 14-of-32 0.8 GB: 15-of-32 1.0 GB: 16-of-32 0.8 GB: 17-of-32 0.8 GB: 18-of-32 1.0 GB: 19-of-32 0.8 GB: 20-of-32 0.8 GB: 21-of-32 1.0 GB: 22-of-32 0.8 GB: 23-of-32 0.8 GB: 24-of-32 1.0 GB: 25-of-32 0.8 GB: 26-of-32 0.8 GB: 27-of-32 1.0 GB: 28-of-32 0.8 GB: 29-of-32 0.8 GB: 30-of-32 1.6 GB: 31-of-32 0.8 GB: 32-of-32
Supported Languages	zh en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.55.4
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the QiMing Weaver capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to QiMing Weaver

Best Alternatives	Context / RAM	Downloads	Likes
...JA Qwen3 14B Agentic 256K V0.1	256K / 29.5 GB	28	8
SimpleChat 14B V1	195K / 29.5 GB	10	2
...0528DistillQwen 14B V27.3 200K	195K / 29.5 GB	9	5
...uct 21B Brainstorm20x 128K Ctx	128K / 84.1 GB	8	0
NousCoder 14B	80K / 29.5 GB	379	221
MiroThinker 14B DPO V0.2	64K / 29.7 GB	28	6
UIGEN T3 14B Preview	40K / 29.5 GB	24	22
Qwen3 14B	40K / 29.7 GB	2722973	437
Hermes 4 14B	40K / 29.5 GB	194693	169
Qwen3 14B NVFP4	40K / 10.6 GB	125214	13

Note: green Score (e.g. "73.2") means that the model is better than aifeifei798/QiMing-Weaver.