What are the hardware requirements for EVA Yi 1.5 9B 32K V1?

EVA Yi 1.5 9B 32K V1 requires approximately 17.7 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed EVA Yi 1.5 9B 32K V1 and how large is it?

EVA Yi 1.5 9B 32K V1 is developed by EVA-UNIT-01, a model with 9b parameters. 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 EVA Yi 1.5 9B 32K V1?

EVA Yi 1.5 9B 32K V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EVA Yi 1.5 9B 32K V1 by EVA-UNIT-01 — VRAM 17.7GB, 32K context

Name: EVA Yi 1.5 9B 32K V1
Author: EVA-UNIT-01

EVA Yi 1.5 9B 32K V1 is an open-source language model by EVA-UNIT-01. Features: 9b LLM, VRAM: 17.7GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14.

Dataset:allura-org/celeste-1.x... Dataset:kalomaze/opus instruct... Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1

EVA Yi 1.5 9B 32K V1 Parameters and Internals

Model Type

RP, storywriting

Additional Notes

Continuation of nothingiisreal's Celeste 1.x series designed to improve stability and versatility, while maintaining unique writing style.

Training Details

Data Sources:

Celeste 70B 0.1 data mixture minus Opus Instruct subset, Kalomaze's Opus_Instruct_25k dataset, filtered for refusals

Methodology:

full-parameter finetune

Hardware Used:

4x3090Ti for 5 days

Input Output

Input Format:

ChatML

Performance Tips:

Recommend using original BFloat16 weights; quantization affects Yi significantly more than other model architectures.

LLM Name	EVA Yi 1.5 9B 32K V1
Repository 🤗	https://huggingface.co/EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1
Base Model(s)	AuriAetherwiing/Yi-1.5-9B-32K-tokfix AuriAetherwiing/Yi-1.5-9B-32K-tokfix
Model Size	9b
Required VRAM	17.7 GB
Updated	2026-07-17
Maintainer	EVA-UNIT-01
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 2.8 GB: 4-of-4 0.0 GB
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.45.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the EVA Yi 1.5 9B 32K V1 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 EVA Yi 1.5 9B 32K V1

Best Alternatives	Context / RAM	Downloads	Likes
SekhmetX 9B V0.1 Test	256K / 21.2 GB	71	2
SekmetX 9B V0.1 Test	256K / 21.2 GB	69	2
Mike Hawk 9B	256K / 21.3 GB	3	3
Xgen Small 9B Instruct R	256K / 42.5 GB	44	11
Yi Coder 9B Chat Instruct TIES	128K / 17.7 GB	25	0
EuroLLM 9B Instruct 2512	32K / 18.3 GB	5898	8
...ity Instruct 3M 0625 Yi 1.5 9B	4K / 17.7 GB	8543	4
ChinaLM 9B	4K / 17.9 GB	13	1
Llama 3 Experiment V1 9B GGUF	8K / 5.4 GB	256	0

Note: green Score (e.g. "73.2") means that the model is better than EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1.