What are the hardware requirements for YiSM 34B 0rn?

YiSM 34B 0rn requires approximately 67.8 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 YiSM 34B 0rn and how large is it?

YiSM 34B 0rn is developed by altomek, 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 YiSM 34B 0rn perform on standard benchmarks?

YiSM 34B 0rn has the following published scores: MMLU 78.51. Compare against reference models on this page or on the LLM Explorer leaderboards.

YiSM 34B 0rn by altomek — VRAM 67.8GB, 4K context

Name: YiSM 34B 0rn
Author: altomek

YiSM 34B 0rn is an open-source language model by altomek. Features: 34b LLM, VRAM: 67.8GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.26, Arc: 69.5, HellaSwag: 86.7, MMLU: 78.5, GSM8K: 75.8.

Base model:01-ai/yi-1.5-34b Base model:01-ai/yi-1.5-34b-ch... Base model:merge:01-ai/yi-1.5-... Base model:merge:01-ai/yi-1.5-... Conversational Endpoints compatible Llama Merge Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/altomek/YiSM-34B-0rn

YiSM 34B 0rn Parameters and Internals

Model Type

text generation

Additional Notes

Fits in 16GB VRAM but not recommended for performance in lower quants.

LLM Name	YiSM 34B 0rn
Repository 🤗	https://huggingface.co/altomek/YiSM-34B-0rn
Base Model(s)	01-ai/Yi-1.5-34B-Chat 01-ai/Yi-1.5-34B 01-ai/Yi-1.5-34B-Chat 01-ai/Yi-1.5-34B
Model Size	34b
Required VRAM	67.8 GB
Updated	2026-08-05
Maintainer	altomek
Model Type	llama
Model Files	2.0 GB: 1-of-36 1.9 GB: 2-of-36 1.9 GB: 3-of-36 1.9 GB: 4-of-36 2.0 GB: 5-of-36 1.9 GB: 6-of-36 1.9 GB: 7-of-36 1.9 GB: 8-of-36 2.0 GB: 9-of-36 1.9 GB: 10-of-36 1.9 GB: 11-of-36 1.9 GB: 12-of-36 2.0 GB: 13-of-36 1.9 GB: 14-of-36 1.9 GB: 15-of-36 1.9 GB: 16-of-36 2.0 GB: 17-of-36 1.9 GB: 18-of-36 1.9 GB: 19-of-36 1.9 GB: 20-of-36 2.0 GB: 21-of-36 1.9 GB: 22-of-36 1.9 GB: 23-of-36 1.9 GB: 24-of-36 2.0 GB: 25-of-36 1.9 GB: 26-of-36 1.9 GB: 27-of-36 1.9 GB: 28-of-36 2.0 GB: 29-of-36 1.9 GB: 30-of-36 1.9 GB: 31-of-36 1.9 GB: 32-of-36 2.0 GB: 33-of-36 1.9 GB: 34-of-36 1.4 GB: 35-of-36 0.9 GB: 36-of-36
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	float16

Rank the YiSM 34B 0rn 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 YiSM 34B 0rn

Best Alternatives	Context / RAM	Downloads	Likes
Bagel Hermes 34B Slerp	195K / 68.9 GB	8375	1
34B Beta	195K / 69.2 GB	8670	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	9133	320
Bagel 34B V0.2	195K / 68.7 GB	259	41
Yi 34B 200K AEZAKMI V2	195K / 69.2 GB	57	12
Faro Yi 34B	195K / 69.2 GB	8208	6
Bagel DPO 34B V0.5	195K / 68.7 GB	8040	17
Smaug 34B V0.1 ExPO	195K / 69.2 GB	7812	0