What are the hardware requirements for Yi 1.5 34B Chat?

Yi 1.5 34B Chat requires approximately 69.2 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 Yi 1.5 34B Chat and how large is it?

Yi 1.5 34B Chat is developed by 01-ai, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Yi 1.5 34B Chat perform on standard benchmarks?

Yi 1.5 34B Chat has the following published scores: MMLU 77.08, LMSYS ELO 1212. Compare against reference models on this page or on the LLM Explorer leaderboards.

Yi 1.5 34B Chat by 01-ai — VRAM 69.2GB, 4K context

Name: Yi 1.5 34B Chat
Rating: 1 (1 reviews)
Author: 01-ai

Yi 1.5 34B Chat is an open-source language model by 01-ai. Features: 34b LLM, VRAM: 69.2GB, Context: 4K, License: apache-2.0, HF Score: 74.8, LLM Explorer Score: 0.41, ELO: 1212, Arc: 70.5, HellaSwag: 86, MMLU: 77.1, TruthfulQA: 62.2, WinoGrande: 81.6, GSM8K: 71.7.

Arxiv:2403.04652 Conversational Deploy:azure Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/01-ai/Yi-1.5-34B-Chat

Yi 1.5 34B Chat Benchmarks

LMSys ELO: 1212 vs 1272 (so35)^-4.7%

IFEval: 60.67 vs 88 (so35)^-31.1%

ARC: 70.48 vs 96.7 (so35)^-27.1%

HellaSwag: 85.97 vs 95.3 (gpt4)^-9.8%

MMLU: 77.08 vs 88.3 (so35)^-12.7%

TruthfulQA: 62.16 vs 59 (gpt4)^5.4%

WinoGrande: 81.61 vs 87.5 (gpt4)^-6.7%

GSM8K: 71.65 vs 96.4 (so35)^-25.7%

MATH Lvl 5: 27.72

LLME Score: 0.41218

^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 🚀

Yi 1.5 34B Chat Parameters and Internals

Model Type

Chat, Base

Training Details

Data Sources:

High-quality corpus, Diverse fine-tuning samples

Data Volume:

500B tokens

LLM Name	Yi 1.5 34B Chat
Repository 🤗	https://huggingface.co/01-ai/Yi-1.5-34B-Chat
Model Size	34b
Required VRAM	69.2 GB
Updated	2026-04-22
Maintainer	01-ai
Model Type	llama
Model Files	4.8 GB: 1-of-15 4.8 GB: 2-of-15 5.0 GB: 3-of-15 4.8 GB: 4-of-15 4.8 GB: 5-of-15 5.0 GB: 6-of-15 4.8 GB: 7-of-15 4.8 GB: 8-of-15 5.0 GB: 9-of-15 4.8 GB: 10-of-15 4.8 GB: 11-of-15 5.0 GB: 12-of-15 4.8 GB: 13-of-15 4.8 GB: 14-of-15 1.2 GB: 15-of-15
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Quantized Models of the Yi 1.5 34B Chat

Model	Likes	Downloads	VRAM
Yi 1.5 34B Chat AWQ	2	876	19 GB
Yi 1.5 34B Chat GGUF	5	122	12 GB
Yi 1.5 34B Chat GGUF	4	82	8 GB
Yi 1.5 34B Chat GPTQ	1	9	19 GB

Best Alternatives to Yi 1.5 34B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Bagel Hermes 34B Slerp	195K / 68.9 GB	8078	1
34B Beta	195K / 69.2 GB	8253	66
Smaug 34B V0.1	195K / 69.2 GB	8313	64
Yi 34B 200K	195K / 68.9 GB	10271	320
Casual Magnum 34B	195K / 68.8 GB	13	1
Bagel 34B V0.2	195K / 68.7 GB	2752	41
Yi 34B 200K AEZAKMI V2	195K / 69.2 GB	537	12
Smaug 34B V0.1 ExPO	195K / 69.2 GB	7738	0
Bagel DPO 34B V0.5	195K / 68.7 GB	8131	17
Faro Yi 34B	195K / 69.2 GB	8230	6

Rank the Yi 1.5 34B Chat 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? 53472 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

Yi 1.5 34B Chat by 01-ai