SE

Sea Lion 7b

SeaGGUF by mradermacherUpdated 2025-04-16
Download on Hugging Face
Parameters7.5B
Context2K
Layers32
Architecturempt
Smallest quant2.1 GB
Quick answer

Sea Lion 7b needs about 9.8 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.1 GB (IQ1_S) to 6.2 GB (Q6_K).

Sea Lion 7b – a 7.5B‑parameter MPT model for Southeast Asian languages

Sea Lion 7b is a 7.5B‑parameter MPT decoder trained on 980B tokens. It supports English, Chinese, Indonesian, Malay, Thai, Vietnamese, Filipino, Tamil, Burmese, Khmer, and Lao. The model is released under the MIT license.

Good at

  • Instruct‑tuned for SEA regional context
  • Supports a wide range of Southeast Asian languages
  • Optimized for 2048‑token context

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No mixture‑of‑experts

Best for

  • Local language generation for SEA regions
  • Fine‑tuning on regional datasets
  • Chatbot deployments with limited VRAM

Who it’s for. Developers and researchers needing a multilingual LLM focused on Southeast Asian languages. The model is suitable for applications that require instruction following and contextual understanding within the SEA region.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.1 GB 3.7 GB
Fits Get file →
IQ1_M2.2 GB 3.8 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.7 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K_S3.1 GB 4.7 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
Q2_K3.3 GB 4.9 GB
Fits Get file →
IQ3_XS3.6 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
Q3_K_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_M4.3 GB 5.8 GB
Fits Get file →
IQ4_XS4.3 GB 5.9 GB
Fits Get file →
IQ4_NL4.5 GB 6.1 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.6 GB 6.1 GB
Fits Get file →
Q3_K_L4.6 GB 6.2 GB
Fits Get file →
Q4_14.9 GB 6.5 GB
Fits Get file →
Q4_K_M5.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.3 GB 6.9 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.2 GB 7.8 GB
Tight Get file →

For 8‑GB VRAM, use IQ1_S (2.1 GB file, 6.9 GB memory) or IQ1_M (2.23 GB, 7 GB). With 12‑GB VRAM, Q4_K_M (5.01 GB, 9.8 GB) or Q5_K_M (5.69 GB, 10.5 GB) are suitable. Higher quants like Q6_K (6.19 GB, 11 GB) need 16‑GB or more.

What GPU do you need for Sea Lion 7b?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K_S (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 11.0 GB in use).

Which Sea Lion 7b quant should you choose?

Q4_K_M is the usual starting point for Sea Lion 7b: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is IQ1_S at 2.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturempt
Parameters7.5B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilySea
Licensemit
Downloads (HF)704
Last updated2025-04-16

Frequently asked questions about Sea Lion 7b

How much VRAM does Sea Lion 7b need?

About 9.8 GB at Q4_K_M with an 8K context window. That is the 5.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Sea Lion 7b on an 8 GB GPU?

Yes, with Q2_K_S: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sea Lion 7b GGUF?

It depends on the quant: IQ1_S is 2.1 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.7 GB, IQ2_M is 2.9 GB and 18 more.

What context length does Sea Lion 7b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download Sea Lion 7b GGUF?

The files are on Hugging Face in the mradermacher/sea-lion-7b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Sea Lion 7b use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Sea Lion 7b on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM, with memory usage around 6.9–7 GB at 8‑k context.

Does Sea Lion 7b support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of SEA-LION-v1-7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sea models

All Sea →

Other small models

All small models →