Llama-3.1-Swallow-8B-Instruct-v0.5

Name: Llama-3.1-Swallow-8B-Instruct-v0.5
Author: Hugging Face

llama3.38B

Llama 3.1 Swallow is a series of large language models (8B, 70B) that were built by continual pre-training on the Meta Llama 3.1 models. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities.

Context

131K

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

Details

Model IDtokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5

ProviderHugging Face

Creatortokyotech-llm

FamilyLlama-3.1

Licensellama3.3

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters8B

Architecturetransformer

Context window131K tokens

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2025-06-12

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Family Comparison: Llama-3.1

Model	Caps	Perf	Speed	Context	Max out
Llama-3.1-8B-Instruct	TS	—	—	131K	—
Llama-3.1-70B-Instruct	TSF	—	—	131K	131K
Llama-3.1-8B-Instruct	TSF	—	—	131K	131K
Meta-Llama-3.1-8B-Instruct-abliterated	TSF	—	—	131K	—
Meta-Llama-3.1-70B-Instruct	TSF	—	—	131K	—
Meta-Llama-3.1-8B-Instruct	TSF	—	—	131K	—
Llama-3.1-8B-Instruct-FP8	TSF	—	—	131K	—
Llama-3.1-Nemotron-70B-Instruct-HF	TSF	—	—	131K	—
Llama-3.1-Swallow-8B-Instruct-v0.5	TSF	—	—	131K	—
Llama-3.1-8B-Instruct	TSF	—	—	131K	—
Meta-Llama-3.1-8B-Instruct	TSF	—	—	131K	—

API

GET/v1/models/huggingface/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5