Skip to content
localllm
日本語

TheBloke

Swallow-70B

Parameters
69.2B
Max context length
4,096
Architecture
llama
License
Conditional
Base model
tokyotech-llm/Swallow-70b-hf
License
llama2

About Swallow-70B

Swallow-70B is a GGUF model based on tokyotech-llm/Swallow-70b-hf on Hugging Face. GGUF files are published by TheBloke/Swallow-70B-GGUF. It has about 69.2B parameters, the llama architecture, a maximum context length of 4,096 tokens (values written in the GGUF).

There are 10 quantizations, with file sizes from 29.4 GB (Q2_K) to 48.9 GB (Q5_K_M) (actual sizes on Hugging Face).

The original model is licensed under Llama 2 Community License, which allows commercial use with conditions such as scale or purpose. Check the original license for the terms of use.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

TheBloke/Swallow-70B-GGUF

Published by the original developer About this label

Last checked: Nov 10, 2026

Architecture
llama
Supported before llama.cpp b4409
Parameters
69.2B
Max context length
4,096
License
llama2 Conditional
File size and memory per quantization for Swallow-70B (TheBloke/Swallow-70B-GGUF)
Quantization File size Measured Quality guide 4,096 max
Q2_K 29.4 GB Very large 31.4 GB
Q3_K_S 30.0 GB Large 32.0 GB
Q3_K_M 33.3 GB Medium 35.3 GB
Q3_K_L 36.3 GB Medium 38.2 GB
Q4_0 39.0 GB Medium 41.0 GB
Q4_K_S 39.2 GB Medium 41.2 GB
Q4_K_M 41.5 GB Small 43.5 GB
Q5_0 47.6 GB Small 49.6 GB
Q5_K_S 47.6 GB Small 49.6 GB
Q5_K_M 48.9 GB Very small 50.9 GB 
Ollama  ollama run hf.co/TheBloke/Swallow-70B-GGUF:Q4_K_M
llama.cpp  llama-server -hf TheBloke/Swallow-70B-GGUF:Q4_K_M

License and commercial use

Llama 2 Community License Conditional

Allows commercial use. However, products or services with more than 700 million monthly active users need a separate license from Meta. You must follow the Acceptable Use Policy.

Based on the license on the original model's Hugging Face page. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Example commands using Q4_K_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/TheBloke/Swallow-70B-GGUF:Q4_K_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf TheBloke/Swallow-70B-GGUF:Q4_K_M

LM Studio

Paste TheBloke/Swallow-70B-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Swallow-70B (Q4_K_M)?
The file size is 41.5 GB (measured). With a 4,096-token context, the estimated memory including the KV cache is 43.5 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Swallow-70B be used commercially?
The original model's license is Llama 2 Community License (Commercial use with conditions).Allows commercial use. However, products or services with more than 700 million monthly active users need a separate license from Meta. You must follow the Acceptable Use Policy. Check the original license text before deciding.
What is the command to run Swallow-70B with Ollama?
Run "ollama run hf.co/TheBloke/Swallow-70B-GGUF:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.