What are the hardware requirements for Deepmoney 34B 200K Base?

Deepmoney 34B 200K Base requires approximately 68.9 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 Deepmoney 34B 200K Base and how large is it?

Deepmoney 34B 200K Base is developed by TriadParty, 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 Deepmoney 34B 200K Base perform on standard benchmarks?

Deepmoney 34B 200K Base has the following published scores: MMLU 74.04. Compare against reference models on this page or on the LLM Explorer leaderboards.

Deepmoney 34B 200K Base by TriadParty — VRAM 68.9GB, 195K context

Name: Deepmoney 34B 200K Base
Author: TriadParty

Deepmoney 34B 200K Base is an open-source language model by TriadParty. Features: 34b LLM, VRAM: 68.9GB, Context: 195K, License: apache-2.0, LLM Explorer Score: 0.15, Arc: 64, HellaSwag: 83.9, MMLU: 74.

En Endpoints compatible Finance Invest Llama Pytorch Region:us Sharded Zh

Model Card on HF 🤗: https://huggingface.co/TriadParty/deepmoney-34b-200k-base

Deepmoney 34B 200K Base Benchmarks

ARC: 63.99 vs 96.7 (so35)^-33.8%

HellaSwag: 83.87 vs 95.3 (gpt4)^-12%

MMLU: 74.04 vs 88.3 (so35)^-16.1%

LLME Score: 0.14579

^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)

Deepmoney 34B 200K Base (TriadParty/deepmoney-34b-200k-base)

🌟 Advertise your project 🚀

Deepmoney 34B 200K Base Parameters and Internals

Model Type

Financial Analysis, Investment Judgments

Use Cases

Areas:

Finance, Investing

Applications:

Investment Judgments, Qualitative and Quantitative Analysis

Primary Use Cases:

Investment pipeline creation, Information collection, Target judgment, Qualitative analysis, Quantitative analysis, Data extraction

Considerations:

For most retail investors, using a model like Deepmoney instead of waiting for an analyst's report is recommended.

Additional Notes

Deepmoney is positioned as a cornerstone model in a larger pipeline for financial analysis, incorporating several specific analysis models.

Training Details

Data Sources:

College textbooks, Professional books, Research report data from 2019 to December 2023

Methodology:

Full parameter training on Yi-34b model with long context (200k tokens)

Context Length:

200000

LLM Name	Deepmoney 34B 200K Base
Repository 🤗	https://huggingface.co/TriadParty/deepmoney-34b-200k-base
Model Size	34b
Required VRAM	68.9 GB
Updated	2026-05-24
Maintainer	TriadParty
Model Type	llama
Model Files	10.0 GB: 1-of-7 9.9 GB: 2-of-7 9.8 GB: 3-of-7 9.8 GB: 4-of-7 9.8 GB: 5-of-7 9.9 GB: 6-of-7 9.7 GB: 7-of-7
Supported Languages	en zh
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

Quantized Models of the Deepmoney 34B 200K Base

Model	Likes	Downloads	VRAM
Deepmoney 34B 200K Base GGUF	15	505	12 GB
Deepmoney 34B 200K Base GPTQ	3	12	18 GB
Deepmoney 34B 200K Base AWQ	1	6	19 GB

Best Alternatives to Deepmoney 34B 200K Base

Best Alternatives	Context / RAM	Downloads	Likes
Bagel Hermes 34B Slerp	195K / 68.9 GB	8375	1
34B Beta	195K / 69.2 GB	8242	66
Smaug 34B V0.1	195K / 69.2 GB	8479	64
Yi 34B 200K	195K / 68.9 GB	10110	320
Casual Magnum 34B	195K / 68.8 GB	4	1
Bagel 34B V0.2	195K / 68.7 GB	943	41
Yi 34B 200K AEZAKMI V2	195K / 69.2 GB	223	12
Bagel DPO 34B V0.5	195K / 68.7 GB	8242	17
Faro Yi 34B	195K / 69.2 GB	8476	6
Smaug 34B V0.1 ExPO	195K / 69.2 GB	7738	0

Note: green Score (e.g. "73.2") means that the model is better than TriadParty/deepmoney-34b-200k-base.

Rank the Deepmoney 34B 200K Base 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? 54415 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

Deepmoney 34B 200K Base by TriadParty