What are the hardware requirements for PocketWeights Qwen2.5 14B Coder Creative?

PocketWeights Qwen2.5 14B Coder Creative requires approximately 29.3 GB of VRAM and supports a context window of 986K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed PocketWeights Qwen2.5 14B Coder Creative and how large is it?

PocketWeights Qwen2.5 14B Coder Creative is developed by PocketWeights, 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 PocketWeights Qwen2.5 14B Coder Creative?

PocketWeights Qwen2.5 14B Coder Creative is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

PocketWeights Qwen2.5 14B Coder Creative by PocketWeights — VRAM 29.3GB, 986K context

Name: PocketWeights Qwen2.5 14B Coder Creative
Author: PocketWeights

PocketWeights Qwen2.5 14B Coder Creative is an open-source language model by PocketWeights. Features: 14b LLM, VRAM: 29.3GB, Context: 986K, License: apache-2.0, Instruction-Based, Code Generating, Merged, LLM Explorer Score: 0.31.

Merged Model Abliterated Base model:qq591503/qwen2.5-14... Base model:qwen/qwen2.5-coder-... Codegen Coder Conversational Dare ties Endpoints compatible Instruct Pocketweights Qwen2 Qwen2.5 Region:us Safetensors Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/PocketWeights/PocketWeights-Qwen2.5-14B-Coder-Creative

PocketWeights Qwen2.5 14B Coder Creative Parameters and Internals

LLM Name	PocketWeights Qwen2.5 14B Coder Creative
Repository 🤗	https://huggingface.co/PocketWeights/PocketWeights-Qwen2.5-14B-Coder-Creative
Base Model(s)	Qwen/Qwen2.5-Coder-14B-Instruct qq591503/Qwen2.5-14B-Instruct-1M-abliterated Qwen/Qwen2.5-Coder-14B-Instruct qq591503/Qwen2.5-14B-Instruct-1M-abliterated
Merged Model	Yes
Model Size	14b
Required VRAM	29.3 GB
Updated	2026-08-31
Maintainer	PocketWeights
Model Type	qwen2
Instruction-Based	Yes
Model Files	1.6 GB: 1-of-16 2.0 GB: 2-of-16 1.9 GB: 3-of-16 2.0 GB: 4-of-16 2.0 GB: 5-of-16 1.9 GB: 6-of-16 1.9 GB: 7-of-16 1.9 GB: 8-of-16 1.9 GB: 9-of-16 1.9 GB: 10-of-16 1.9 GB: 11-of-16 1.9 GB: 12-of-16 1.9 GB: 13-of-16 1.9 GB: 14-of-16 1.9 GB: 15-of-16 0.8 GB: 16-of-16
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	1010000
Model Max Length	1010000
Transformers Version	5.12.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Errors	replace

Rank the PocketWeights Qwen2.5 14B Coder Creative 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 PocketWeights Qwen2.5 14B Coder Creative

Best Alternatives	Context / RAM	Downloads	Likes
ZYH LLM Qwen2.5 14B V4	986K / 29.7 GB	27	8
Qwen2.5 14B YOYO V4	986K / 29.7 GB	20	5
ZYH LLM Qwen2.5 14B V2	986K / 29.7 GB	14	1
ZYH LLM Qwen2.5 14B V5	986K / 29.7 GB	12	8
Qwen2.5 14B YOYO V5	986K / 29.7 GB	10	4
Mergekit Model Stock Ggfjmyf	986K / 29.7 GB	14	0
Mergekit Model Stock Injkqri	986K / 29.7 GB	5	1
...1 DeepSeekR1 Coder 14B Preview	128K / 29.7 GB	9	3
Tessa T1 14B	117K / 29.7 GB	6	13
UIGEN T1.5 14B	117K / 29.7 GB	8	6