What are the hardware requirements for SeaLLM 7B V2.5?

SeaLLM 7B V2.5 requires approximately 17.1 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 SeaLLM 7B V2.5 and how large is it?

SeaLLM 7B V2.5 is developed by SeaLLMs, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does SeaLLM 7B V2.5 perform on standard benchmarks?

SeaLLM 7B V2.5 has the following published scores: MMLU 64.93. Compare against reference models on this page or on the LLM Explorer leaderboards.

SeaLLM 7B V2.5 by SeaLLMs — VRAM 17.1GB, 8K context

Name: SeaLLM 7B V2.5
Author: SeaLLMs

SeaLLM 7B V2.5 is an open-source language model by SeaLLMs. Features: 7b LLM, VRAM: 17.1GB, Context: 8K, License: other, HF Score: 69.1, LLM Explorer Score: 0.24, Arc: 63.5, HellaSwag: 81.5, MMLU: 64.9, TruthfulQA: 53.8, WinoGrande: 76.3, GSM8K: 74.4.

Model Card on HF 🤗: https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5

SeaLLM 7B V2.5 Benchmarks

IFEval: 45.22 vs 88 (so35)^-48.6%

ARC: 63.48 vs 96.7 (so35)^-34.4%

HellaSwag: 81.54 vs 95.3 (gpt4)^-14.4%

MMLU: 64.93 vs 88.3 (so35)^-26.5%

TruthfulQA: 53.78 vs 59 (gpt4)^-8.8%

WinoGrande: 76.32 vs 87.5 (gpt4)^-12.8%

GSM8K: 74.37 vs 96.4 (so35)^-22.9%

MATH Lvl 5: 10.88

LLME Score: 0.23972

^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)

🌟 Advertise your project 🚀

SeaLLM 7B V2.5 Parameters and Internals

LLM Name	SeaLLM 7B V2.5
Repository 🤗	https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5
Model Size	7b
Required VRAM	17.1 GB
Updated	2026-04-10
Maintainer	SeaLLMs
Model Type	gemma
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 2.1 GB: 4-of-4
Supported Languages	en zh vi id th ms km lo my tl
Model Architecture	GemmaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	bfloat16

Quantized Models of the SeaLLM 7B V2.5

Model	Likes	Downloads	VRAM
SeaLLM 7B V2.5 AWQ	2	10	7 GB
SeaLLM 7B V2.5 AWQ	0	5	5 GB
...LM 7B V2.5 ORPO SARAA M 1 GGUF	0	6	5 GB
...aLLM 7B V2.5 ORPO SARAA S GGUF	0	7	5 GB
...aLLM 7B V2.5 ORPO SARAA M.GGUF	0	7	5 GB
...ary Vietnamese Article V1 Gguf	0	6	5 GB
...aLLM 7B V2.5 ORPO SARAA M GGUF	0	6	9 GB
SeaLLM 7B V2.5 4bit	0	6	5 GB

Best Alternatives to SeaLLM 7B V2.5

Best Alternatives	Context / RAM	Downloads	Likes
Kaggle Math Model Gemma V1	12K / 17.1 GB	5	0
Gemma 1.1 7B It	8K / 17.1 GB	20065	275
Gemma 1.1 7B It	8K / 17.1 GB	28	4
Gemma 7B It	8K / 17.1 GB	1029	10
Zephyr 7B Gemma DPO Avg	8K / 17.1 GB	15	0
Zephyr 7B Gemma Rpo Avg	8K / 17.1 GB	7	0
... Codegemma 2 7B It Alpaca V1.3	8K / 17.1 GB	9	1
Zephyr 7B Gemma V0.1	8K / 17.1 GB	302	124
... 7B Finetuned Sft Navarasa 2.0	8K / 34 GB	314	23
Codegemma 7B It	8K / 17.1 GB	3605	251

Note: green Score (e.g. "73.2") means that the model is better than SeaLLMs/SeaLLM-7B-v2.5.

Rank the SeaLLM 7B V2.5 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? 53254 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

SeaLLM 7B V2.5 by SeaLLMs