SA

SambaLingo Thai Base

SambalingoGGUF by mradermacherUpdated 2024-12-11
Download on Hugging Face
Parameters6.95B
Context4K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

SambaLingo Thai Base needs about 9.0 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 1.6 GB (IQ1_S) to 5.7 GB (Q6_K).

SambaLingo Thai Base – a 6.95B Llama‑2‑based Thai/English language model

SambaLingo Thai Base is a 6.95B parameter Llama‑2 model fine‑tuned on Thai and English data. It supports 4096‑token context and is released under the llama2 license. The model is available in multiple GGUF quantizations.

Good at

  • Thai and English text generation
  • Few‑shot prompting
  • Translation between Thai and English

Limits

  • No vision support
  • Requires 4096‑token context
  • License restricts commercial use unless approved

Best for

  • Chatbot prototypes in Thai
  • Translation tasks between Thai and English
  • Educational language learning tools

Who it’s for. Developers building Thai language applications who need a pretrained Llama‑2 model. Researchers interested in bilingual Thai/English language modeling may also use this model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 4.3 GB
Fits Get file →
IQ1_M1.8 GB 4.4 GB
Fits Get file →
IQ2_XXS2.0 GB 4.6 GB
Fits Get file →
IQ2_XS2.1 GB 4.8 GB
Fits Get file →
IQ2_S2.3 GB 5.0 GB
Fits Get file →
Q2_K_S2.4 GB 5.1 GB
Fits Get file →
IQ2_M2.5 GB 5.1 GB
Fits Get file →
Q2_K2.7 GB 5.3 GB
Fits Get file →
IQ3_XXS2.7 GB 5.3 GB
Fits Get file →
IQ3_XS2.9 GB 5.6 GB
Fits Get file →
IQ3_S3.1 GB 5.7 GB
Fits Get file →
Q3_K_S3.1 GB 5.7 GB
Fits Get file →
IQ3_M3.2 GB 5.9 GB
Fits Get file →
Q3_K_M3.4 GB 6.1 GB
Fits Get file →
Q3_K_L3.7 GB 6.4 GB
Fits Get file →
IQ4_XS3.8 GB 6.4 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_K_S4.0 GB 6.6 GB
Fits Get file →
Q4_K_M4.2 GB 6.9 GB
Fits Get file →
Q5_K_S4.8 GB 7.5 GB
Tight Get file →
Q5_K_M4.9 GB 7.6 GB
Tight Get file →
Q6_K5.7 GB 8.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.63 GB file, 6.4 GB memory) or IQ1_M (1.76 GB file, 6.6 GB memory). For 12 GB VRAM, Q4_K_M (4.23 GB file, 9 GB memory) or Q5_K_M (4.94 GB file, 9.7 GB memory) are suitable. Memory estimates are approximate.

What GPU do you need for SambaLingo Thai Base?

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 IQ3_M (3.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.5 GB in use).

Which SambaLingo Thai Base quant should you choose?

Q4_K_M is the usual starting point for SambaLingo Thai Base: it balances file size and quality well. Here it is a 4.2 GB file.

If memory is tight, the smallest file is IQ1_S at 1.6 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
Parameters6.95B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
Licensellama2
Downloads (HF)612
Last updated2024-12-11

Frequently asked questions about SambaLingo Thai Base

How much VRAM does SambaLingo Thai Base need?

About 9.0 GB at Q4_K_M with an 8K context window. That is the 4.2 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 SambaLingo Thai Base on an 8 GB GPU?

Yes, with IQ3_M: the 3.2 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 SambaLingo Thai Base GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.1 GB, IQ2_S is 2.3 GB, Q2_K_S is 2.4 GB and 19 more.

What context length does SambaLingo Thai Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download SambaLingo Thai Base GGUF?

The files are on Hugging Face in the mradermacher/SambaLingo-Thai-Base-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 SambaLingo Thai Base use?

Hugging Face lists the license as llama2. 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?

Yes, using IQ1_S or IQ1_M quantizations which require about 6.4–6.6 GB of VRAM at 8k context.

What languages does it support?

Thai and English. The model is fine‑tuned on Thai data with 25% English.

Is it licensed for commercial use?

The model is released under the llama2 license, which requires compliance with its terms for commercial deployment.

Other GGUFs of SambaLingo-Thai-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sambalingo models

All Sambalingo →

Other small models

All small models →