LL

Llama SEA LION v3 70B IT

LlamaGGUF by aisingaporeUpdated 2026-08-25
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Llama SEA LION v3 70B IT needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 26.4 GB (Q2_K) to 141.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Multilingual 70B Llama model tuned for Southeast Asian languages

Llama SEA LION v3 70B IT is a decoder model based on Llama 3.1 architecture. It supports Burmese, Chinese, English, Filipino, Indonesian, Javanese, Khmer, Lao, Malay, Sundanese, Tamil, Thai, and Vietnamese. The model has a context length of 128k tokens.

Good at

  • Instruction following in SEA languages
  • Large context handling
  • Multilingual support

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is Llama 3.1 Community

Best for

  • Chatbots in Southeast Asia
  • Translation between SEA languages
  • Content generation in local languages

Who it’s for. Developers building applications that need robust instruction following across Southeast Asian languages. Researchers exploring multilingual LLM capabilities in the region.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q4_040.0 GB 43.2 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_048.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (3 parts) 78.2 GB
Too big Get file →
F16141.1 GB (8 parts) 144.3 GB
Too big Get file →

For 8‑12 GB VRAM, use Q4_0 (file size 39.97 GB, memory 43.2 GB at 8k context). For 12‑16 GB VRAM, Q4_K_M (42.52 GB, 45.7 GB). For 16‑20 GB VRAM, Q5_0 (48.66 GB, 51.8 GB). Higher precision quants require more memory.

What GPU do you need for Llama SEA LION v3 70B IT?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Llama SEA LION v3 70B IT quant should you choose?

Q4_K_M is the usual starting point for Llama SEA LION v3 70B IT: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 26.4 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

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byaisingapore
FamilyLlama
Licensellama3.1
Downloads (HF)1,529
Last updated2026-08-25

Frequently asked questions about Llama SEA LION v3 70B IT

How much VRAM does Llama SEA LION v3 70B IT need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Llama SEA LION v3 70B IT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama SEA LION v3 70B IT GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_M is 34.3 GB, Q4_0 is 40.0 GB, Q4_K_M is 42.5 GB, Q5_0 is 48.7 GB, Q5_K_M is 49.9 GB and 3 more.

What context length does Llama SEA LION v3 70B IT support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Llama SEA LION v3 70B IT GGUF?

The files are on Hugging Face in the aisingapore/Llama-SEA-LION-v3-70B-IT-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 Llama SEA LION v3 70B IT use?

Hugging Face lists the license as llama3.1. 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 this model on 8 GB VRAM?

Use the Q4_0 quant, which estimates 43.2 GB memory at 8k context; 8 GB VRAM is insufficient.

Does the model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the Llama 3.1 Community License.

Other GGUFs of Llama-SEA-LION-v3-70B-IT

Similar models

Browse all →

More from aisingapore

All by aisingapore →

More Llama models

All Llama →

Other large models

All large models →