Samba 3.8B

Closed weights Microsoft,University of Illinois Urbana-Champaign (UIUC) 3.8B parameters June 2024

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Microsoft,University of Illinois Urbana-Champaign (UIUC)
Organisation type
Industry,Academia
Country
United States of America
Published
11 June 2024
Authors
Liliang Ren, Yang Liu, Yadong Lu, Yelong Shen, Chen Liang, Weizhu Chen

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language modeling/generation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
3.8B

3.8B, table 10

Training data
tokens

3.2T tokens

Epochs
1

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
7.3 × 10²² FLOP

"We scale SAMBA with 421M, 1.3B, 1.7B and up to 3.8B parameters. In particular, the largest 3.8B base model pre-trained with 3.2T tokens achieves a 71.2 score for MMLU [HBB+21], 54.9 for HumanEval [CTJ+21], and 69.6 for GSM8K" 3.8B * 3.2T * 6 = 7.3e22

How it was established
Operation counting

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

training code: https://github.com/microsoft/Samba

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Last updated
28 November 2025

What the numbers mean

What this model is

Samba 3.8B was published by Microsoft,University of Illinois Urbana-Champaign (UIUC), in United States of America, in June 2024. It comes out of industry,Academia.

It works in Language, and is recorded as doing language modeling/generation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Training it took roughly 7.3 × 10²² FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Answers

Samba 3.8B — common questions

01

Is Samba 3.8B open source?

No. Samba 3.8B has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Samba 3.8B have?

Samba 3.8B has 3.8B parameters. 3.8B, table 10. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Who created Samba 3.8B?

Samba 3.8B was published by Microsoft,University of Illinois Urbana-Champaign (UIUC), based in United States of America, categorised as industry,Academia.

04

When was Samba 3.8B released?

Samba 3.8B was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Samba 3.8B used for?

Samba 3.8B works in Language, and is recorded as handling language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

How much compute was used to train Samba 3.8B?

Around 7.3 × 10²² FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

07

What GPU do I need to run Samba 3.8B?

None. Samba 3.8B is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.