Tomorrow
← Chips & Compute

Intel Gaudi 3

Intel · #9 most active of 18 in Chips & Compute

Compare →

Gaudi 3 targets price-performance against Nvidia parts with open Ethernet scale-out and an oneAPI/PyTorch software path.

50

Trust score · Mixed

2 data points checked · 2026-11-02

Model stack: ContradictedVersion: VerifiedHow this works →

Current version

1.24.2

Entry cost

Pricing not publicly listed (contact Intel sales or cloud partners)

Changes / 30d

3

The short answers · verified November 3, 2026

What is the latest version of Intel Gaudi 3?
The current shipped version of Intel Gaudi 3 is 1.24.2, as of November 3, 2026.
How much does Intel Gaudi 3 cost?
Intel Gaudi 3 has no published flat entry price. Pricing not publicly listed (contact Intel sales or cloud partners)
What AI model does Intel Gaudi 3 use?
Intel Gaudi 3 runs primarily on Accelerator.

Source: Intel — docs.habana.ai · Reusable under CC BY 4.0 — cite Tomorrow

Capabilities

  • 128GB HBM2e
  • Open Ethernet scale-out
  • PyTorch native
  • oneAPI toolchain
  • Price-performance focus
  • PyTorch Support
  • vLLM Integration
  • DeepSpeed Training
  • SGLang Support
  • FP8 Training
  • Quantization (UINT4, NF4)
  • Hugging Face Optimum
  • Triton Inference Server
  • TPC Programming
  • HCCL (Habana Collective Communications Library)
  • GPU Migration Toolkit
  • DeepSpeed Support
  • FP8 Training & Inference
  • Hugging Face Optimum Integration
  • Distributed Training (HCCL)
  • Quantized Inference (UINT4/NF4)
  • Triton & TorchServe Model Serving
  • PyTorch Training
  • DeepSpeed
  • vLLM Plugin
  • SGLang
  • HPU Graphs
  • Inference with Quantization
  • HCCL
  • Inference
  • vLLM Support
  • Model Serving
  • Distributed Training
  • Havana Collective Communications Library (HCCL)
  • Transformer Engine
  • vLLM Inference
  • SGLang Inference
  • FP8 / INT4 Quantization
  • HCCL Collective Communications
  • Kubernetes Orchestration
  • PyTorch
  • vLLM
  • INT4 Inference
  • TorchServe
  • Quantization (FP8, INT4, NF4)
  • H HCCL
  • Quantization
  • PyTorch training
  • FP8 training
  • vLLM inference
  • DeepSpeed support
  • SGLang support
  • HPU graphs
  • DeepSpeed Integration
  • INT4 Quantization
  • Quantization (FP8/UINT4/NF4)
  • FP8/INT4 Quantization
  • HCCL scale-out
  • Inference Serving
  • Quantization (INT4/NF4)
  • Inference using vLLM
  • Inference using SGLang
  • HCCL Scale-out
  • Intel Gaudi Software Suite
  • PyTorch Inference
  • Mixed Precision Training
  • UINT4 Inference
  • NF4 Inference
  • Intel Gaudi Profiler
  • hl-smi
  • Habana Collective Communications Library (HCCL)
  • HPU Graphs for Training
  • Quantization (FP8, UINT4, NF4)
  • Habana Labs Management Library (HLML)
  • HCCL Support
  • Quantization (FP8, INT4, NF4, UINT4)
  • Quantization (FP8/INT4/NF4)
  • Inference and Model Serving
  • Kubernetes Integration
  • FP8 Inference
  • Inference serving
  • DeepSpeed Optimization
  • AI Model Serving
  • Quantized Inference (FP8/INT4)
  • AI Training
  • AI Inference
  • SGLang Integration
  • FP8/INT4 Inference

Pricing

  • OEM/cloud

    quoted

    Free

Entry price over time

Not enough pricing history yet — we start charting from the second observation.

Geek mode

Models under the hood

  • Accelerator

    Intel

    disclosed

  • Intel Gaudi 2

    Intel

    disclosed

  • Intel Gaudi 3

    Intel

    disclosed

Context window

n/a

Public API

yes

Multi-model routing

no

Stack signals

  • PyTorch
  • vLLM
  • SGLang
  • DeepSpeed

Shared model stack

Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.

green disclosed · amber inferred · grey unattributed. Aliases are folded into one model; provider concentration counts only models with an established vendor.

Reported scale

Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.

No public usage figure on record for this product.

Public market scorecard

Intel investor relations

Intel trades as NASDAQ: INTC. Figures below are as reported for Q2 2026 on Jul 23, 2026; market levels are the close on Aug 6, 2026 and are a reference marker, not a live quote.

Q2 2026 revenue

~$12.5B

flat YoY

Foundry
still loss-making
18A ramp is the swing factor
Client computing
~$7B

Market reference

Share price~$27
12-month change+20%
Market cap~$120B
Live quote

Also in Chips & Compute

All Chips & Compute
Google TPU Ironwood

Google

11

Inference-first TPU pods

Version
7th-generation (Ironwood)
Cost
from $5.4/unit
Model
Gemini
Cerebras WSE-3

Cerebras

9

Wafer-scale inference and training

Version
CS-4
Cost
Free trial credits available; developer tier has free promotional credits.
Model
Codex-Spark
Tenstorrent Blackhole

Tenstorrent

8

Open RISC-V AI hardware

Version
Blackhole
Cost
from $999/unit
Model
Blackhole Tensix
AWS Trainium2

AWS

7

Cloud-native training silicon

Version
Trainium2
Cost
Pricing is not published on the page. Available via EC2 instances/UltraServers.
Model
Neuron compiler
NVIDIA Blackwell

NVIDIA

5

GB200/B200 rack-scale AI systems

Version
GB200 NVL72
Cost
Pricing is not published (enterprise/quote-only)
Model
Blackwell
AMD Instinct MI355X

AMD

3

High-memory GPU alternative

Version
MI355X
Cost
Enterprise hardware, pricing not published
Model
CDNA

Change history

  • capability

    New capabilities: FP8/INT4 Inference

    87 tracked88 tracked · +FP8/INT4 Inference

    source
  • capability

    New capabilities: AI Training, AI Inference, SGLang Integration

    84 tracked87 tracked · +AI Training, AI Inference, SGLang Integration

    source
  • capability

    New capabilities: AI Model Serving, Quantized Inference (FP8/INT4)

    82 tracked84 tracked · +AI Model Serving, Quantized Inference (FP8/INT4)

    source
  • capability

    New capabilities: Inference serving, DeepSpeed Optimization

    80 tracked82 tracked · +Inference serving, DeepSpeed Optimization

    source
  • capability

    New capabilities: FP8 Inference

    79 tracked80 tracked · +FP8 Inference

    source
  • capability

    New capabilities: Inference and Model Serving, Kubernetes Integration

    77 tracked79 tracked · +Inference and Model Serving, Kubernetes Integration

    source
  • version

    Intel Gaudi 3 moved to 1.24.2

    v1.24.21.24.2

    source
  • capability

    New capabilities: Quantization (FP8/INT4/NF4)

    76 tracked77 tracked · +Quantization (FP8/INT4/NF4)

    source
  • version

    Intel Gaudi 3 moved to v1.24.2

    1.24.2v1.24.2

    source
  • capability

    New capabilities: Quantization (FP8, INT4, NF4, UINT4)

    75 tracked76 tracked · +Quantization (FP8, INT4, NF4, UINT4)

    source
  • capability

    New capabilities: HCCL Support

    74 tracked75 tracked · +HCCL Support

    source
  • version

    Intel Gaudi 3 moved to 1.24.2

    1.24.11.24.2

    source
  • capability

    New capabilities: Habana Labs Management Library (HLML)

    73 tracked74 tracked · +Habana Labs Management Library (HLML)

    source
  • capability

    New capabilities: HPU Graphs for Training, Quantization (FP8, UINT4, NF4)

    71 tracked73 tracked · +HPU Graphs for Training, Quantization (FP8, UINT4, NF4)

    source
  • capability

    New capabilities: Habana Collective Communications Library (HCCL)

    70 tracked71 tracked · +Habana Collective Communications Library (HCCL)

    source
  • capability

    New capabilities: Intel Gaudi Profiler, hl-smi

    68 tracked70 tracked · +Intel Gaudi Profiler, hl-smi

    source
  • capability

    New capabilities: UINT4 Inference, NF4 Inference

    66 tracked68 tracked · +UINT4 Inference, NF4 Inference

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • capability

    New capabilities: Mixed Precision Training

    65 tracked66 tracked · +Mixed Precision Training

    source
  • capability

    New capabilities: PyTorch Inference

    64 tracked65 tracked · +PyTorch Inference

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • capability

    New capabilities: Intel Gaudi Software Suite

    63 tracked64 tracked · +Intel Gaudi Software Suite

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • capability

    New capabilities: Inference using vLLM, Inference using SGLang, HCCL Scale-out

    60 tracked63 tracked · +Inference using vLLM, Inference using SGLang, HCCL Scale-out

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • capability

    New capabilities: Inference Serving, Quantization (INT4/NF4)

    58 tracked60 tracked · +Inference Serving, Quantization (INT4/NF4)

    source
  • capability

    New capabilities: FP8/INT4 Quantization, HCCL scale-out

    56 tracked58 tracked · +FP8/INT4 Quantization, HCCL scale-out

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • capability

    New capabilities: Quantization (FP8/UINT4/NF4)

    55 tracked56 tracked · +Quantization (FP8/UINT4/NF4)

    source
  • version

    Intel Gaudi 3 moved to 1.24.1

    1.24.01.24.1

    source
  • version

    Intel Gaudi 3 moved to 1.24.0

    1.24.11.24.0

    source
  • capability

    New capabilities: DeepSpeed Integration, INT4 Quantization

    53 tracked55 tracked · +DeepSpeed Integration, INT4 Quantization

    source
  • capability

    New capabilities: PyTorch training, FP8 training, vLLM inference

    47 tracked53 tracked · +PyTorch training, FP8 training, vLLM inference, DeepSpeed support, SGLang support, HPU graphs

    source
Subscribe to Intel Gaudi 3 changes

Intel Gaudi 3 compared

Straight head-to-head pages against the busiest products in Chips & Compute.

Intel Gaudi 3 vs Google TPU IronwoodIntel Gaudi 3 vs Cerebras WSE-3Intel Gaudi 3 vs Tenstorrent BlackholeIntel Gaudi 3 vs AWS Trainium2Intel Gaudi 3 vs NVIDIA BlackwellIntel Gaudi 3 vs AMD Instinct MI355X

How to cite this page

Free to cite and reuse under CC BY 4.0. Permalink: https://tomorrow.aliensquad.ai/tools/intel-gaudi-3

APA
Tomorrow. (2026). Intel Gaudi 3 — version, pricing and model stack [Data set entry]. AlienSquad. Retrieved 2026-11-08, from https://tomorrow.aliensquad.ai/tools/intel-gaudi-3
BibTeX
@misc{tomorrow-tools-intel-gaudi-3,
  author       = {{Tomorrow}},
  title        = {Intel Gaudi 3 — version, pricing and model stack},
  year         = {2026},
  publisher    = {AlienSquad},
  howpublished = {\url{https://tomorrow.aliensquad.ai/tools/intel-gaudi-3}},
  note         = {Accessed: 2026-11-08}
}