What are the hardware requirements for Qwen14b 4 12?

Qwen14b 4 12 requires approximately 29.7 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen14b 4 12 and how large is it?

Qwen14b 4 12 is developed by BKM1804, a model with 14.8b 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 Qwen14b 4 12?

Qwen14b 4 12 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen14b 4 12 by BKM1804 — VRAM 29.7GB, 32K context

Name: Qwen14b 4 12
Author: BKM1804

Qwen14b 4 12 is an open-source language model by BKM1804. Features: 14.8b LLM, VRAM: 29.7GB, Context: 32K, LLM Explorer Score: 0.18.

Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/BKM1804/qwen14b-4-12

Qwen14b 4 12 Parameters and Internals

LLM Name	Qwen14b 4 12
Repository 🤗	https://huggingface.co/BKM1804/qwen14b-4-12
Model Size	14.8b
Required VRAM	29.7 GB
Updated	2026-08-09
Maintainer	BKM1804
Model Type	qwen2
Model Files	5.0 GB: 1-of-6 5.0 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 5.0 GB: 5-of-6 4.7 GB: 6-of-6
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.50.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	151665
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen14b 4 12 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 Qwen14b 4 12

Best Alternatives	Context / RAM	Downloads	Likes
Viper Coder V1.7 Vsm6	986K / 29.7 GB	9	6
Cheng 2 Ingredient4	986K / 29.7 GB	6	0
...acilla Vipercoderv1.7vsm6 0308	986K / 29.7 GB	7	0
Temp Model For 2 Mini 006	986K / 29.7 GB	8	0
Tempmotacilla Cinerea 0308	128K / 29.7 GB	11	2
...irtuoso Small V2 Tensopolis V1	128K / 29.7 GB	5	1
Merge Model 20250308 2	128K / 29.7 GB	6	0
Tempesthenno Kto 0205 Ckpt80	128K / 29.6 GB	5	3
Viper Coder Hybrid V1.3	128K / 29.7 GB	16	9
Miisce One	128K / 29.7 GB	8	2

Note: green Score (e.g. "73.2") means that the model is better than BKM1804/qwen14b-4-12.