What are the hardware requirements for Cria Llama2 7B V1.3 GGML?

Cria Llama2 7B V1.3 GGML requires approximately 3.8 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Cria Llama2 7B V1.3 GGML and how large is it?

Cria Llama2 7B V1.3 GGML is developed by davzoku, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Cria Llama2 7B V1.3 GGML perform on standard benchmarks?

Cria Llama2 7B V1.3 GGML has the following published scores: MMLU 48.3. Compare against reference models on this page or on the LLM Explorer leaderboards.

Cria Llama2 7B V1.3 GGML by davzoku — VRAM 3.8GB, 4K context

Name: Cria Llama2 7B V1.3 GGML
Author: davzoku

Cria Llama2 7B V1.3 GGML is an open-source language model by davzoku. Features: 7b LLM, VRAM: 3.8GB, Context: 4K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.11, Arc: 52.7, HellaSwag: 78.6, MMLU: 48.3, GSM8K: 8.5.

Codegen Dataset:mlabonne/codellama-2-2... En Ggml Llama Llama2 Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/davzoku/cria-llama2-7b-v1.3-GGML

Cria Llama2 7B V1.3 GGML Parameters and Internals

Model Type

text generation, chatbot

Use Cases

Areas:

chatbots, intelligent applications

Primary Use Cases:

chatbot system, model deployment

Training Details

Data Sources:

mlabonne/CodeLlama-2-20k

Methodology:

Fine-tuned with QLoRA (4-bit precision)

Hardware Used:

T4 GPU, High RAM

Release Notes

Version:

v1.3

Notes:

CRIA v1.3 released with multiple model variants

LLM Name	Cria Llama2 7B V1.3 GGML
Repository 🤗	https://huggingface.co/davzoku/cria-llama2-7b-v1.3-GGML
Base Model(s)	davzoku/cria-llama2-7b-v1.3 davzoku/cria-llama2-7b-v1.3
Model Size	7b
Required VRAM	3.8 GB
Updated	2026-07-30
Maintainer	davzoku
Model Type	llama
Model Files	3.8 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Cria Llama2 7B V1.3 GGML 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 Cria Llama2 7B V1.3 GGML

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 7B Java 16bit	16K / 13.5 GB	10	0
Codellama 7B Bnb 4bit	16K / 3.9 GB	3695	9
...ruct Solidity Bnb 4bit Smashed	16K / 4.2 GB	6	0
...lama 7B Tofuagent Contpretrain	16K / 13.5 GB	6	0
...B Instruct Hf Bnb 4bit Smashed	16K / 4.2 GB	6	0
CodeLlama 7B Python Onnx Fp16	16K / GB	5	1
CodeLlama 7B Python 4bit MLX	16K / 4 GB	235	14
CodelLama7B Inst DPO 7K Mlx	16K / 4.2 GB	49	4
...pMagic Coder 7B 8.0bpw H8 EXL2	16K / 6.9 GB	3	1
...eLlama 7B Instruct Hf 4bit MLX	16K / 4.2 GB	84	3

Note: green Score (e.g. "73.2") means that the model is better than davzoku/cria-llama2-7b-v1.3-GGML.