What are the hardware requirements for 35B Beta2ep?

35B Beta2ep requires approximately 69.5 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 35B Beta2ep and how large is it?

35B Beta2ep is developed by CausalLM, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does 35B Beta2ep perform on standard benchmarks?

35B Beta2ep has the following published scores: MMLU 79.5. Compare against reference models on this page or on the LLM Explorer leaderboards.

35B Beta2ep by CausalLM — VRAM 69.5GB, 8K context

Name: 35B Beta2ep
Author: CausalLM

35B Beta2ep is an open-source language model by CausalLM. Features: 35b LLM, VRAM: 69.5GB, Context: 8K, License: gpl-3.0, Instruction-Based, LLM Explorer Score: 0.13, Arc: 64.4, HellaSwag: 83.7, MMLU: 79.5, GSM8K: 43.3.

Cohere Conversational Dataset:baai/coig Dataset:causallm/refined-anime... Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-3.... Dataset:josephuscheung/guanaco... Dataset:ldjnr/puffin Dataset:liwu/mnbvc Dataset:m-a-p/codefeedback-fil... Dataset:meta-math/metamathqa Dataset:microsoft/orca-math-wo... Dataset:milashkaarshif/moegirl... Dataset:ryokoai/fandom23k Dataset:ryokoai/sharegpt52k Dataset:teknium/openhermes Dataset:tigerresearch/tigerbot... Dataset:wiki lingua Dataset:wikipedia Dataset:wizardlm/wizardlm evol... De En Endpoints compatible Instruct Ja Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/CausalLM/35b-beta2ep

35B Beta2ep Parameters and Internals

Additional Notes

No loras, no quants, no tricks. Recommended for general tasks, knowledge, coding.

Supported Languages

en (full), zh (full), ja (full), de (full)

Training Details

Data Sources:

JosephusCheung/GuanacoDataset, meta-math/MetaMathQA, jondurbin/airoboros-3.1, WizardLM/WizardLM_evol_instruct_V2_196k, RyokoAI/ShareGPT52K, RyokoAI/Fandom23K, milashkaarshif/MoeGirlPedia_wikitext_raw_archive, wikipedia, wiki_lingua, garage-bAInd/Open-Platypus, LDJnr/Puffin, BAAI/COIG, TigerResearch/tigerbot-zhihu-zh-10k, liwu/MNBVC, teknium/openhermes, CausalLM/Refined-Anime-Text, microsoft/orca-math-word-problems-200k, m-a-p/CodeFeedback-Filtered-Instruction

Methodology:

Fully fine-tuned at 128K+ ~30M entries long, web crawl input, GPT-4-32k/3.5-16k output, synthetic dataset

Context Length:

128000

Training Time:

1 epoch

Input Output

Input Format:

web crawl input, synthetic dataset

Output Format:

GPT-4-32k/3.5-16k output

LLM Name	35B Beta2ep
Repository 🤗	https://huggingface.co/CausalLM/35b-beta2ep
Model Size	35b
Required VRAM	69.5 GB
Updated	2026-09-23
Maintainer	CausalLM
Model Type	cohere
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-15 4.9 GB: 2-of-15 4.9 GB: 3-of-15 4.9 GB: 4-of-15 4.9 GB: 5-of-15 4.9 GB: 6-of-15 4.9 GB: 7-of-15 4.9 GB: 8-of-15 4.9 GB: 9-of-15 4.9 GB: 10-of-15 4.9 GB: 11-of-15 4.9 GB: 12-of-15 4.9 GB: 13-of-15 4.9 GB: 14-of-15 1.1 GB: 15-of-15
Supported Languages	en zh ja de
Model Architecture	CohereForCausalLM
License	gpl-3.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<PAD>
Vocabulary Size	256000
Torch Data Type	bfloat16

Rank the 35B Beta2ep 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 35B Beta2ep

Best Alternatives	Context / RAM	Downloads	Likes
...ommand R V01 Japanese Instruct	8K / 69.5 GB	140	4
35B Beta Long	8K / 69.5 GB	99	69