What are the hardware requirements for NexusRaven 13B?

NexusRaven 13B requires approximately 26 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 and how large is it?

NexusRaven 13B is developed by Nexusflow, 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?

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

NexusRaven 13B by Nexusflow — VRAM 26GB, 16K context

Name: NexusRaven 13B
Author: Nexusflow

NexusRaven 13B is an open-source language model by Nexusflow. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.09.

Arxiv:2308.12950 Base model:codellama/codellama... Base model:finetune:codellama/... Codegen Endpoints compatible Instruct Llama Pytorch Region:us Sharded

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

NexusRaven 13B Parameters and Internals

Model Type

text-generation

Use Cases

Limitations:

We highly recommend using a stop criteria of ["\nReflection:"]. The model was trained to first generate an answer and then reflect on its answer to either improve the answer or keep the answer the same. However, this "chain of thought" is often not helpful, and the final answer is seldom better than the initial call. Therefore, we strongly recommend using the Initial Call as the main call to execute., The model works best when it is connected with a retriever when there are a multitude of functions, as a large number of functions will saturate the context window of this model., The model can be prone to generate incorrect calls. Please ensure proper guardrails to capture errant behavior is in place.

Training Details

Hardware Used:

multi-GPU

Input Output

Performance Tips:

We highly recommend stopping the model generation at a stopping criteria of ["\nReflection:"], to avoid spending unnecessary tokens during inference.

LLM Name	NexusRaven 13B
Repository 🤗	https://huggingface.co/Nexusflow/NexusRaven-13B
Base Model(s)	CodeLlama 13B Instruct Hf codellama/CodeLlama-13b-Instruct-hf
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-06
Maintainer	Nexusflow
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3 0.0 GB
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 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

Quantized Models of the NexusRaven 13B

Model	Likes	Downloads	VRAM
NexusRaven 13B GGUF	21	355	5 GB
NexusRaven 13B GPTQ	7	35	7 GB
NexusRaven 13B AWQ	4	22	7 GB

Best Alternatives to NexusRaven 13B

Best Alternatives	Context / RAM	Downloads	Likes
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
Panda Coder 13B	16K / 26 GB	11	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	8	28
Gen Sim	16K / 0.3 GB	4	3
CodeLlama 13B Instruct Fp16	16K / 26 GB	137	28
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3

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