What are the hardware requirements for Deepseekq?

Deepseekq requires approximately 4.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseekq and how large is it?

Deepseekq is developed by Ammartatox, 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 Deepseekq perform on standard benchmarks?

Deepseekq has the following published scores: MMLU 44. Compare against reference models on this page or on the LLM Explorer leaderboards.

Deepseekq by Ammartatox — VRAM 4.2GB

Name: Deepseekq
Author: Ammartatox

Deepseekq is an open-source language model by Ammartatox. Features: 7b LLM, VRAM: 4.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.15, Arc: 42.5, HellaSwag: 56.1, MMLU: 44, GSM8K: 55.6.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... En Endpoints compatible Gguf Llama Quantized Region:us Unsloth

Model Card on HF 🤗: https://huggingface.co/Daemontatox/Deepseekq

Deepseekq Parameters and Internals

LLM Name	Deepseekq
Repository 🤗	https://huggingface.co/Daemontatox/Deepseekq
Base Model(s)	Deepseek Llm 7B Chat deepseek-ai/deepseek-llm-7b-chat
Model Size	7b
Required VRAM	4.2 GB
Updated	2024-08-11
Maintainer	Ammartatox
Model Type	llama
Model Files	13.8 GB 4.2 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModel
License	apache-2.0

Rank the Deepseekq 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 Deepseekq

Best Alternatives	Context / RAM	Downloads	Likes
Pixel	8K / 4.4 GB	17	0
Qwen2 7B Alpacha Q8 0	0K / 9.1 GB	23	0
...ral 7B Instruct V0.2 Llamafile	0K / 14.5 GB	8850	25
Conversely Mistral 7B	0K / 0.2 GB	132	0
Mistral 7B Instruct V0.3 GGUF	0K / 1.6 GB	91691	147
CleverBoi 7B V2	0K / 0.1 GB	586	0
WizardLM 2 7B GGUF	0K / 2.7 GB	93547	83
Qwen2 7B Instruct GGUF	0K / 1.9 GB	56414	10
...hemeng Qwen Math 7b 24 1 100 1	0K / 15.2 GB	25	0
Mistral 7B Instruct V0.2 GGUF	0K / 3.1 GB	70243	511

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