LL

Llama-3-Swallow-70B-v0.1

LlamaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Llama-3-Swallow-70B-v0.1 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 20 quants, from 15.3 GB (IQ1_S) to 49.9 GB (Q5_K_M).

Llama‑3‑Swallow‑70B‑v0.1 – 70.6B parameter Llama model with Japanese and English support

Llama‑3‑Swallow‑70B‑v0.1 is a 70.6B parameter Llama model trained on Japanese and English data. It supports a 8192 token context window and is available in multiple GGUF quantizations. The model is released under the llama3 license.

Good at

  • Japanese language tasks
  • English language tasks
  • Large context reasoning

Limits

  • Requires large VRAM for full precision
  • No vision support
  • License restricts commercial use

Best for

  • Japanese text generation
  • English text generation
  • Research on multilingual LLMs

Who it’s for. Developers and researchers needing a large Japanese‑English Llama model. The model is suitable for fine‑tuning or inference on high‑end GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q4_040.1 GB 43.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.34 GB file, 18.5 GB memory). For 12 GB VRAM, IQ1_M (16.75 GB file, 19.9 GB memory). For 16 GB VRAM, IQ2_XS (21.14 GB file, 24.3 GB memory). Higher‑quality quants such as Q4_K_M or Q5_K_M require 45–53 GB memory and are suitable for 24 GB or larger GPUs.

What GPU do you need for Llama-3-Swallow-70B-v0.1?

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: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 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-3-Swallow-70B-v0.1 quant should you choose?

Q4_K_M is the usual starting point for Llama-3-Swallow-70B-v0.1: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is IQ1_S at 15.3 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 context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)1,944
Last updated2024-08-02

Frequently asked questions about Llama-3-Swallow-70B-v0.1

How much VRAM does Llama-3-Swallow-70B-v0.1 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-3-Swallow-70B-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama-3-Swallow-70B-v0.1 GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 14 more.

What context length does Llama-3-Swallow-70B-v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Llama-3-Swallow-70B-v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Llama-3-Swallow-70B-v0.1-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 Llama-3-Swallow-70B-v0.1 use?

Hugging Face lists the license as llama3. 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 Llama‑3‑Swallow‑70B‑v0.1 on 8 GB VRAM?

Use the IQ1_S quant, which requires 18.5 GB memory at 8 k context. 8 GB VRAM is insufficient for inference.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the llama3 license.

Other GGUFs of Llama-3-Swallow-70B-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →