What are the hardware requirements for Dolphin 2.9.1 Yi 1.5 34B?

Dolphin 2.9.1 Yi 1.5 34B requires approximately 69.2 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dolphin 2.9.1 Yi 1.5 34B and how large is it?

Dolphin 2.9.1 Yi 1.5 34B is developed by cognitivecomputations, 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 Dolphin 2.9.1 Yi 1.5 34B perform on standard benchmarks?

Dolphin 2.9.1 Yi 1.5 34B has the following published scores: MMLU 77.52. Compare against reference models on this page or on the LLM Explorer leaderboards.

Dolphin 2.9.1 Yi 1.5 34B by cognitivecomputations — VRAM 69.2GB, 8K context

Name: Dolphin 2.9.1 Yi 1.5 34B
Author: cognitivecomputations

Dolphin 2.9.1 Yi 1.5 34B is an open-source language model by cognitivecomputations. Features: 34b LLM, VRAM: 69.2GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.33, Arc: 69.4, HellaSwag: 85.5, MMLU: 77.5, GSM8K: 73.

Autotrain compatible Axolotl Base model:01-ai/yi-1.5-34b Base model:finetune:01-ai/yi-1... Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:internlm/agent-flan Dataset:locutusque/function-ca... Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo... Dataset:teknium/openhermes-2.5 Endpoints compatible Generated from trainer Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.9.1-yi-1.5-34b

Dolphin 2.9.1 Yi 1.5 34B Parameters and Internals

Model Type

text generation, multimodal

Training Details

Data Sources:

cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k, Locutusque/function-calling-chatml, internlm/Agent-FLAN

Methodology:

Full-weight fine-tuning with 8k sequence length

Context Length:

4096

Hardware Used:

8xH100 node

Model Architecture:

LlamaForCausalLM

Input Output

Input Format:

ChatML prompt template

Accepted Modalities:

text

LLM Name	Dolphin 2.9.1 Yi 1.5 34B
Repository 🤗	https://huggingface.co/cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
Base Model(s)	01-ai/Yi-1.5-34B 01-ai/Yi-1.5-34B
Model Size	34b
Required VRAM	69.2 GB
Updated	2025-07-13
Maintainer	cognitivecomputations
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	8192
Model Max Length	8192
Transformers Version	4.40.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the Dolphin 2.9.1 Yi 1.5 34B 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

Quantized Models of the Dolphin 2.9.1 Yi 1.5 34B

Model	Likes	Downloads	VRAM
Dolphin 2.9.1 Yi 1.5 34B AWQ	1	2	19 GB

Best Alternatives to Dolphin 2.9.1 Yi 1.5 34B

Best Alternatives	Context / RAM	Downloads	Likes
Bagel Hermes 34B Slerp	195K / 68.9 GB	8375	1
34B Beta	195K / 69.2 GB	8504	67
Smaug 34B V0.1	195K / 69.2 GB	8082	64
Casual Magnum 34B	195K / 68.8 GB	4	1
Yi 34B 200K	195K / 68.9 GB	9020	320
Bagel 34B V0.2	195K / 68.7 GB	259	41
Yi 34B 200K AEZAKMI V2	195K / 69.2 GB	57	12
Smaug 34B V0.1 ExPO	195K / 69.2 GB	7812	0
Faro Yi 34B	195K / 69.2 GB	8208	6
Bagel DPO 34B V0.5	195K / 68.7 GB	8040	17