What are the hardware requirements for Verysmol Llama V11 KIx2?

Verysmol Llama V11 KIx2 requires approximately 0.2 GB of VRAM and supports a context window of 1K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Verysmol Llama V11 KIx2 and how large is it?

Verysmol Llama V11 KIx2 is developed by BEE-spoke-data, a model with 58.1m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Verysmol Llama V11 KIx2 perform on standard benchmarks?

Verysmol Llama V11 KIx2 has the following published scores: MMLU 25.28. Compare against reference models on this page or on the LLM Explorer leaderboards.

Verysmol Llama V11 KIx2 by BEE-spoke-data — VRAM 0.2GB, 1K context

Name: Verysmol Llama V11 KIx2
Author: BEE-spoke-data

Verysmol Llama V11 KIx2 is an open-source language model by BEE-spoke-data. Features: 58.1m LLM, VRAM: 0.2GB, Context: 1K, License: apache-2.0, LLM Explorer Score: 0.14, Arc: 22.7, HellaSwag: 27.6, MMLU: 25.3, GSM8K: 0.3.

Dataset:bee-spoke-data/knowled... Endpoints compatible Generated from trainer Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/BEE-spoke-data/verysmol_llama-v11-KIx2

Verysmol Llama V11 KIx2 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, text generation

Training Details

Data Sources:

KI dataset

Methodology:

Fine-tuning

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text

LLM Name	Verysmol Llama V11 KIx2
Repository 🤗	https://huggingface.co/BEE-spoke-data/verysmol_llama-v11-KIx2
Model Size	58.1m
Required VRAM	0.2 GB
Updated	2026-08-13
Maintainer	BEE-spoke-data
Model Type	llama
Model Files	0.2 GB 0.0 GB
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Transformers Version	4.33.3
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32128
Torch Data Type	float32

Rank the Verysmol Llama V11 KIx2 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