What are the hardware requirements for WomboCombo R1 Coder 14B Preview?

WomboCombo R1 Coder 14B Preview 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 WomboCombo R1 Coder 14B Preview and how large is it?

WomboCombo R1 Coder 14B Preview is developed by RDson, 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 WomboCombo R1 Coder 14B Preview?

WomboCombo R1 Coder 14B Preview is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

WomboCombo R1 Coder 14B Preview by RDson — VRAM 29.7GB, 32K context

Name: WomboCombo R1 Coder 14B Preview
Author: RDson

WomboCombo R1 Coder 14B Preview is an open-source language model by RDson. Features: 14b LLM, VRAM: 29.7GB, Context: 32K, Quantized, Code Generating, LLM Explorer Score: 0.28.

Base model:arcee-ai/supernova-... Base model:deepseek-ai/deepsee... Base model:merge:arcee-ai/supe... Base model:merge:deepseek-ai/d... Base model:merge:qwen/qwen2.5-... Base model:merge:qwen/qwen2.5-... Base model:qwen/qwen2.5-coder-... Base model:qwen/qwen2.5-coder-... Codegen Conversational Endpoints compatible Gguf Merge Mergekit Q8 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/RDson/WomboCombo-R1-Coder-14B-Preview

WomboCombo R1 Coder 14B Preview Parameters and Internals

LLM Name	WomboCombo R1 Coder 14B Preview
Repository 🤗	https://huggingface.co/RDson/WomboCombo-R1-Coder-14B-Preview
Base Model(s)	Qwen/Qwen2.5-Coder-14B-Instruct DeepSeek R1 Distill Qwen 14B SuperNova Medius Qwen/Qwen2.5-Coder-14B Qwen/Qwen2.5-Coder-14B-Instruct deepseek-ai/DeepSeek-R1-Distill-Qwen-14B arcee-ai/SuperNova-Medius Qwen/Qwen2.5-Coder-14B
Model Size	14b
Required VRAM	29.7 GB
Updated	2026-08-06
Maintainer	RDson
Model Type	qwen2
Model Files	15.7 GB 4.9 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 4.8 GB: 6-of-6
GGUF Quantization	Yes
Quantization Type	q8\|gguf
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the WomboCombo R1 Coder 14B Preview 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 WomboCombo R1 Coder 14B Preview

Best Alternatives	Context / RAM	Downloads	Likes
...er 14B Instruct Abliterated V1	32K / 29.7 GB	7	3
Shed Coder 0.2	128K / 9.9 GB	16	0
CogitoZ14	32K / 29.7 GB	25	1
Strand Rust Coder 14B V1 4bit	32K / 8.3 GB	56	1
....5 Coder 14B Instruct Bnb 4bit	32K / 9.9 GB	21134	5
UIGEN T1.1 Qwen 14B	32K / 29.7 GB	1130	32
Qwen 14B Codefourchan	32K / 29.7 GB	2	1
...wen2.5 Coder 14B Instruct 4bit	32K / 8.3 GB	2879	8
UIGEN T1.1 Qwen 14B	32K / 29.7 GB	95	41
Qwen2.5 Coder 14B Bnb 4bit	32K / 9.9 GB	1398	6