What are the hardware requirements for NexusRaven V2 13B?

NexusRaven V2 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 V2 13B and how large is it?

NexusRaven V2 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.

How does NexusRaven V2 13B perform on standard benchmarks?

NexusRaven V2 13B has the following published scores: MMLU 44.88. Compare against reference models on this page or on the LLM Explorer leaderboards.

NexusRaven V2 13B by Nexusflow — VRAM 26GB, 16K context

Name: NexusRaven V2 13B
Rating: 4 (1 reviews)
Author: Nexusflow

NexusRaven V2 13B is an open-source language model by Nexusflow. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: other, Instruction-Based, Code Generating, HF Score: 48.2, LLM Explorer Score: 0.18, Arc: 45.1, HellaSwag: 67.4, MMLU: 44.9, TruthfulQA: 44.5, WinoGrande: 66.4, GSM8K: 20.9.

Arxiv:2308.12950 Base model:codellama/codellama... Base model:finetune:codellama/... Codegen Endpoints compatible Function calling Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Nexusflow/NexusRaven-V2-13B

NexusRaven V2 13B Benchmarks

IFEval: 17.91 vs 88 (so35)^-79.6%

ARC: 45.14 vs 96.7 (so35)^-53.3%

HellaSwag: 67.4 vs 95.3 (gpt4)^-29.3%

MMLU: 44.88 vs 88.3 (so35)^-49.2%

TruthfulQA: 44.54 vs 59 (gpt4)^-24.5%

WinoGrande: 66.38 vs 87.5 (gpt4)^-24.1%

GSM8K: 20.92 vs 96.4 (so35)^-78.3%

MATH Lvl 5: 2.95

LLME Score: 0.17731

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

NexusRaven V2 13B (Nexusflow/NexusRaven-V2-13B)

🌟 Advertise your project 🚀

NexusRaven V2 13B Parameters and Internals

Model Type

function calling

Use Cases

Primary Use Cases:

function calling

Limitations:

The model can be prone to generate incorrect calls and explanations., Works best when connected with a retriever when numerous functions are present.

LLM Name	NexusRaven V2 13B
Repository 🤗	https://huggingface.co/Nexusflow/NexusRaven-V2-13B
Base Model(s)	CodeLlama 13B Instruct Hf codellama/CodeLlama-13b-Instruct-hf
Model Size	13b
Required VRAM	26 GB
Updated	2026-04-13
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
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.33.0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32024
Torch Data Type	bfloat16

Quantized Models of the NexusRaven V2 13B

Model	Likes	Downloads	VRAM
NexusRaven V2 13B AWQ	3	11	7 GB
NexusRaven V2 13B GGUF	50	358	5 GB
NexusRaven V2 13B AWQ	1	19	7 GB
NexusRaven V2 13B GPTQ	3	4	7 GB

Best Alternatives to NexusRaven V2 13B

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 13B Instruct Hf	16K / 26 GB	5282	159
CodeLlama 13B MORepair	16K / 26 GB	12	2
CodeLlama 13B Instruct Hf	16K / 26 GB	234	27
TableLLM 13B	16K / 26 GB	306	32
NexusRaven 13B	16K / 26 GB	17	105
Panda Coder 13B	16K / 26 GB	20	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	42	28
Gen Sim	16K / 0.3 GB	8	3
CodeLlama 13B Instruct Fp16	16K / 26 GB	903	28
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	346	3

Rank the NexusRaven V2 13B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53185 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

NexusRaven V2 13B by Nexusflow