Llama-3.1-8B-Instruct-FP8

llama3.18B
Context
131K

Capabilities

Reasoning & Interaction
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Model IDnvidia/Llama-3.1-8B-Instruct-FP8
Provider Hugging Face
Creator NVIDIA
FamilyLlama-3.1
Licensellama3.1
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters8B
Architecturetransformer
Context window131K tokens
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Family Comparison: Llama-3.1

ModelContextMax out
Llama-3.1-8B-Instruct131K—
Llama-3.1-70B-Instruct131K131K
Llama-3.1-8B-Instruct131K131K
Meta-Llama-3.1-8B-Instruct-abliterated131K—
Meta-Llama-3.1-70B-Instruct131K—
Meta-Llama-3.1-8B-Instruct131K—
Llama-3.1-8B-Instruct-FP8131K—
Llama-3.1-Nemotron-70B-Instruct-HF131K—
Llama-3.1-Swallow-8B-Instruct-v0.5131K—
Llama-3.1-8B-Instruct131K—
Meta-Llama-3.1-8B-Instruct131K—

API

GET/v1/models/huggingface/nvidia/Llama-3.1-8B-Instruct-FP8

Llama-3.1-8B-Instruct-FP8

nvidia/Llama-3.1-8B-Instruct-FP8
Changes · 4 entries
nvidia/Llama-3.1-8B-Instruct-FP8update1cd659eMar 24, 2026, 04:19 AM
capabilitiesfine tuningyes
nvidia/Llama-3.1-8B-Instruct-FP8updateb301ebeMar 23, 2026, 11:47 PM
modalitiesinput["text"]output["text"]
nvidia/Llama-3.1-8B-Instruct-FP8update2b100acMar 23, 2026, 05:30 AM
capabilitiestool callyes
familyLlama-3.1
model_typechat
parameters8
page_urlhttps://huggingface.co/nvidia/Llama-3.1-8B-Instruct-FP8
release_date2024-08-29
context_window131072
licensellama3.1
architecturetransformer
open_weightyes
tools["function_calling"]
nvidia/Llama-3.1-8B-Instruct-FP8create7f5c66fMar 21, 2026, 05:16 AM