What are the hardware requirements for Koboldcpp?

Koboldcpp requires a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Koboldcpp and how large is it?

Koboldcpp is developed by concedo. 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 Koboldcpp?

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

Koboldcpp by concedo — 2K context

Name: Koboldcpp
Author: concedo

Koboldcpp is an open-source language model by concedo. Features: LLM, Context: 2K, License: other, Quantized, LLM Explorer Score: 0.07.

En Gguf Opt Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/concedo/koboldcpp

Koboldcpp Benchmarks

LLME Score: 0.07226

^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)

🌟 Advertise your project 🚀

Koboldcpp Parameters and Internals

Additional Notes

This is a placeholder model for a llamacpp powered KoboldAI API emulator. It is not intended for direct use and is necessary for API compatibility within the official KoboldAI client.

Supported Languages

en (Expert)

LLM Name	Koboldcpp
Repository 🤗	https://huggingface.co/concedo/koboldcpp
Required VRAM	0 GB
Updated	2026-05-17
Maintainer	concedo
Model Type	opt
Model Files	0.0 GB 0.0 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	OPTForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.24.0
Vocabulary Size	50266
Torch Data Type	float16
Activation Function	relu

Best Alternatives to Koboldcpp

Best Alternatives	Context / RAM	Downloads	Likes
Spacescience	2K / 3.2 GB	5	0
Synthetic4	2K / 3.2 GB	7	0
Core 350	2K / 1.3 GB	5	0
...Step3 Rlhf Actor Model Opt1.3B	2K / 3.2 GB	14	1
...IJM80K5NJ0153L8H6P0LKGBH46O1FR	2K / 5.3 GB	96	0
...IJGEDTROT8NYV94YHO91YCQTDMMSP4	2K / 5.3 GB	93	0
...23J4QWZMIQMDHE11LW81CTY8YWQ0GZ	2K / 5.3 GB	93	0
...8X7SO3BQJ205L6RBNEZSIZRCMSIW2V	2K / 5.3 GB	96	0
...U9GJ1CY8NQ8VVSDE18915SJI08HEJX	2K / 5.3 GB	10	0
...DN7HWZK26MU53SK114P5LBFVET1MDY	2K / 5.3 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than concedo/koboldcpp.

Rank the Koboldcpp 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? 53972 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

Koboldcpp by concedo

» All LLMs » concedo » Koboldcpp URL Share it on

Koboldcpp Benchmarks

Koboldcpp Parameters and Internals

Best Alternatives to Koboldcpp

Rank the Koboldcpp Capabilities

What open-source LLMs or SLMs are you in search of? 53972 in total.