What are the hardware requirements for NexusRaven 13B GPTQ?

NexusRaven 13B GPTQ requires approximately 7.3 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NexusRaven 13B GPTQ and how large is it?

NexusRaven 13B GPTQ is developed by TheBloke, a model with 13b 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 NexusRaven 13B GPTQ?

NexusRaven 13B GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NexusRaven 13B GPTQ by TheBloke — VRAM 7.3GB, 16K context

Name: NexusRaven 13B GPTQ
Author: TheBloke

NexusRaven 13B GPTQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.3GB, Context: 16K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.09.

Arxiv:2308.12950 4-bit Base model:nexusflow/nexusrave... Base model:quantized:nexusflow... Codegen Gptq Instruct Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/NexusRaven-13B-GPTQ

NexusRaven 13B GPTQ Parameters and Internals

Model Type

llama

Use Cases

Limitations:

Stop criteria of ["\nReflection:"] recommended, Works best with a retriever for a multitude of functions, Prone to generate incorrect calls, requires guardrails

Additional Notes

The model is commercially viable and surpasses state-of-the-art in function calling capabilities.

Training Details

Methodology:

Fine-tuned version of codellama/CodeLlama-13b-Instruct-hf

Input Output

Input Format:

{prompt}

LLM Name	NexusRaven 13B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/NexusRaven-13B-GPTQ
Model Name	Nexusraven 13B
Model Creator	Nexusflow
Base Model(s)	NexusRaven 13B Nexusflow/NexusRaven-13B
Model Size	13b
Required VRAM	7.3 GB
Updated	2026-07-28
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	7.3 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.33.2
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32024
Torch Data Type	bfloat16

Rank the NexusRaven 13B GPTQ 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 NexusRaven 13B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 13B Instruct GPTQ	16K / 7.3 GB	75	39
CodeLlama 13B Instruct Fp16	16K / 26 GB	137	28
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3
...13B Instruct Nf4 Fp16 Upscaled	16K / 26 GB	6	0
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
CodeLlama 13B Instruct GGUF	16K / 5.4 GB	611	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/NexusRaven-13B-GPTQ.