SE

SeaLLM 7B v2.5

SeallmGGUF by QuantFactoryUpdated 2024-04-18
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturellama
Smallest quant3.5 GB
Quick answer

SeaLLM 7B v2.5 needs about 8.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 3.5 GB (Q2_K) to 9.1 GB (Q8_0).

SeaLLM 7B v2.5 – a multilingual LLM for Southeast Asian languages

SeaLLM 7B v2.5 is a 8.54‑billion‑parameter model built on the llama architecture. It supports 8192‑token context and is optimized for SEA languages. The model is released as a GGUF package with multiple quantizations.

Good at

  • Multilingual knowledge tasks
  • Math reasoning
  • Instruction following

Limits

  • No vision support
  • License is other
  • No explicit language list

Best for

  • Chatbots in SEA languages
  • Educational content generation
  • Local knowledge retrieval

Who it’s for. Developers building applications that require strong performance on Southeast Asian languages. The model is suitable for local deployment with llama.cpp or llama.cpp‑compatible runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.5 GB 6.8 GB
Fits Get file →
Q3_K_S4.0 GB 7.3 GB
Tight Get file →
Q3_K_M4.4 GB 7.7 GB
Tight Get file →
Q3_K_L4.7 GB 8.0 GB
Too big Get file →
Q4_05.0 GB 8.3 GB
Too big Get file →
Q4_K_S5.0 GB 8.4 GB
Too big Get file →
Q4_K_M5.3 GB 8.6 GB
Too big Get file →
Q4_15.5 GB 8.8 GB
Too big Get file →
Q5_06.0 GB 9.3 GB
Too big Get file →
Q5_K_S6.0 GB 9.3 GB
Too big Get file →
Q5_K_M6.1 GB 9.5 GB
Too big Get file →
Q5_16.5 GB 9.8 GB
Too big Get file →
Q6_K7.0 GB 10.3 GB
Too big Get file →
Q8_09.1 GB 12.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (5.01 GB file, 8.3 GB memory) or Q4_K_S (5.05 GB file, 8.4 GB memory). For 12 GB VRAM, Q6_K (7.01 GB file, 10.3 GB memory) or Q8_0 (9.08 GB file, 12.4 GB memory) are suitable. Memory estimates are approximate.

What GPU do you need for SeaLLM 7B v2.5?

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 Q3_K_L (4.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 10.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 12.4 GB in use).

Which SeaLLM 7B v2.5 quant should you choose?

Q4_K_M is the usual starting point for SeaLLM 7B v2.5: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 9.1 GB, about 1.7 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 3.5 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
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized byQuantFactory
FamilySeallm
Licenseother
Downloads (HF)1,092
Last updated2024-04-18

Frequently asked questions about SeaLLM 7B v2.5

How much VRAM does SeaLLM 7B v2.5 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 5.3 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 SeaLLM 7B v2.5 on an 8 GB GPU?

Yes, with Q3_K_L: the 4.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SeaLLM 7B v2.5 GGUF?

It depends on the quant: Q2_K is 3.5 GB, Q3_K_S is 4.0 GB, Q3_K_M is 4.4 GB, Q3_K_L is 4.7 GB, Q4_0 is 5.0 GB, Q4_K_S is 5.0 GB and 8 more.

What context length does SeaLLM 7B v2.5 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download SeaLLM 7B v2.5 GGUF?

The files are on Hugging Face in the QuantFactory/SeaLLM-7B-v2.5-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 SeaLLM 7B v2.5 use?

Hugging Face lists the license as other. 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 SeaLLM 7B v2.5 on 8 GB VRAM?

Yes, the Q4_0 or Q4_K_S quantizations fit within 8 GB VRAM with about 8.3–8.4 GB memory usage.

Does SeaLLM 7B v2.5 support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of SeaLLM-7B-v2.5

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Seallm models

All Seallm →

Other small models

All small models →