LL

Llama 3.1 Swallow 8B Instruct v0.3

LlamaGGUF by mmngaUpdated 2024-12-24
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Llama 3.1 Swallow 8B Instruct v0.3 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.0 GB (IQ1_S) to 8.5 GB (Q8_0).

Llama 3.1 Swallow 8B Instruct v0.3 – 8.03B parameter instruction model

Llama 3.1 Swallow 8B Instruct v0.3 is an 8.03B parameter instruction-following model. It supports up to 8192 context tokens and is available in multiple GGUF quantizations. The model is trained on Japanese and English data.

Good at

  • Instruction following
  • Japanese language support
  • Moderate context length

Limits

  • No vision support
  • Requires at least 3.6 GB VRAM for IQ1_S
  • License: llama3.1

Best for

  • Chatbot development
  • Japanese text generation
  • Instruction-based tasks

Who it’s for. Developers building chat or instruction-based applications that require Japanese language support. The model is suitable for projects that can accommodate the 8.03 B parameter size and the 8192 token context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 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_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_05.6 GB 7.2 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.02 GB) or IQ1_M (2.16 GB). For 12 GB VRAM, Q4_K_M (4.92 GB) or Q5_K_M (5.73 GB) provide a balance of quality and memory. Larger VRAM allows Q6_K (6.6 GB) or Q8_0 (8.54 GB).

What GPU do you need for Llama 3.1 Swallow 8B Instruct v0.3?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which Llama 3.1 Swallow 8B Instruct v0.3 quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 Swallow 8B Instruct v0.3: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 IQ1_S at 2.0 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymmnga
FamilyLlama
Licensellama3.1
Downloads (HF)796
Last updated2024-12-24

Frequently asked questions about Llama 3.1 Swallow 8B Instruct v0.3

How much VRAM does Llama 3.1 Swallow 8B Instruct v0.3 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 3.1 Swallow 8B Instruct v0.3 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.1 Swallow 8B Instruct v0.3 GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 18 more.

What context length does Llama 3.1 Swallow 8B Instruct v0.3 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Llama 3.1 Swallow 8B Instruct v0.3 GGUF?

The files are on Hugging Face in the mmnga/tokyotech-llm-Llama-3.1-Swallow-8B-Instruct-v0.3-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 3.1 Swallow 8B Instruct v0.3 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?

Yes, use IQ1_S or IQ1_M quantizations, which estimate 3.6–3.7 GB VRAM at 8k context.

Does this model support Japanese?

Yes, it is trained on Japanese and English data and includes Japanese language support.

What context length does it support?

It supports up to 8192 tokens of context.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Llama models

All Llama →

Other small models

All small models →