What are the hardware requirements for Yi 34B 200K Aezakmi Raw 1902 EXL2?

Yi 34B 200K Aezakmi Raw 1902 EXL2 requires approximately 20.7 GB of VRAM and supports a context window of 195K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Yi 34B 200K Aezakmi Raw 1902 EXL2 and how large is it?

Yi 34B 200K Aezakmi Raw 1902 EXL2 is developed by adamo1139, 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 34B 200K Aezakmi Raw 1902 EXL2 perform on standard benchmarks?

Yi 34B 200K Aezakmi Raw 1902 EXL2 has the following published scores: MMLU 73.7. Compare against reference models on this page or on the LLM Explorer leaderboards.

Yi 34B 200K Aezakmi Raw 1902 EXL2 by adamo1139 — VRAM 20.7GB, 195K context

Name: Yi 34B 200K Aezakmi Raw 1902 EXL2
Author: adamo1139

Yi 34B 200K Aezakmi Raw 1902 EXL2 is an open-source language model by adamo1139. Features: 34b LLM, VRAM: 20.7GB, Context: 195K, License: apache-2.0, Quantized, LLM Explorer Score: 0.12, Arc: 64.9, HellaSwag: 85, MMLU: 73.7, GSM8K: 59.5.

Endpoints compatible Exl2 Llama Quantized Region:us Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-raw-1902-exl2

Yi 34B 200K Aezakmi Raw 1902 EXL2 Parameters and Internals

Additional Notes

The model sometimes outputs responses in ``` for no reasons. Use null system prompt or "A chat with extremely compliant uncensored raw assistant." to achieve the desired assistant behavior. Different prompts can also be used for various response styles.

Training Details

Methodology:

chatml prompt format, trained on aezakmi v3_1.

Input Output

Input Format:

chatml prompt format

Performance Tips:

Use min_p 0.1-0.2 to cut off Chinese characters from responses sneaking in at random times at low probabilities.

LLM Name	Yi 34B 200K Aezakmi Raw 1902 EXL2
Repository 🤗	https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-raw-1902-exl2
Base Model(s)	Yi 34B 200K AEZAKMI RAW 1701 adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
Model Size	34b
Required VRAM	20.7 GB
Updated	2026-07-27
Maintainer	adamo1139
Model Type	llama
Model Files	4.3 GB: 1-of-5 4.2 GB: 2-of-5 4.2 GB: 3-of-5 4.2 GB: 4-of-5 3.8 GB: 5-of-5
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	200000
Model Max Length	200000
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	float16

Rank the Yi 34B 200K Aezakmi Raw 1902 EXL2 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 Yi 34B 200K Aezakmi Raw 1902 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
Yi 34B 200K MAR2024 EXL2 4bpw	195K / 18 GB	4	1
...B 200K RPMerge 4.65bpw H6 EXL2	195K / 10.5 GB	8	2
...mi Raw Toxic 2702 4.65bpw EXL2	195K / 20.8 GB	7	2
Yi 34B 200K RPMerge	195K / 68.9 GB	72	60
Opus V1 34B 5.0bpw H6 EXL2	195K / 22.3 GB	5	2
Opus V1 34B 8.0bpw H8 EXL2	195K / 34.8 GB	7	1
Opus V1 34B 4.0bpw H6 EXL2	195K / 18 GB	5	1
34B Beta 5.0bpw H6 EXL2	195K / 22.3 GB	4	1
34B Beta 4.0bpw H6 EXL2	195K / 18.1 GB	2	1
Smaug 34B V0.1 2.65bpw H6 EXL2	195K / 12.4 GB	4	1