RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
  1. >
  2. Home
  3. /Hardware
  4. /AMD Instinct MI350X
UNIT · AMD · GPU
288 GB VRAMworkstation·Reviewed June 2026

AMD Instinct MI350X

AMD · HARDWARE
AMD Instinct MI350X

No editorial image yet — generic vendor mark shown. Credentials in spec table below.

The air-coolable sibling of the listed MI355X — same CDNA 4 silicon, 288GB HBM3E, ~8 TB/s, at a lower (~1,000W-class) power profile. The variant most non-hyperscale on-prem deployments would actually buy. (TDP figure pending confirmation against AMD's official datasheet.)

Released 2025·8000 GB/s memory bandwidth
RUNLOCALAI SCORE
See full leaderboard →
626/ 1000
BB-tier
Estimated
Throughput
500/ 500
VRAM-fit
200/ 200
Ecosystem
130/ 200
Efficiency
64/ 100

Sub-scores sum to 894 / 1000. Headline = 894 × 0.70 (Estimated-confidence discount) = 626. This is an algorithmic performance-tier score — distinct from, and often lower than, the editorial “Our verdict” below, which weighs value and real-world fit (especially for hardware we haven’t measured yet). How scoring works →

Extrapolated from 8000 GB/s bandwidth — 800.0 tok/s estimated. No measured benchmarks yet.

WORKLOAD FIT
Try other hardware →

Plain-English: Runs 70B comfortably — snappy enough for a coding agent.

7B chat✓
Comfortable
14B chat✓
Comfortable
32B chat✓
Comfortable
70B chat✓
Comfortable
Coding agent✓
Comfortable
Vision (≤8B VLM)~
Tight
Long context (32K)✓
Comfortable
✓Comfortable — fits with headroom
~Tight — works, no slack
△Marginal — needs aggressive quant
✗Doesn't fit usefully

Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.

BLK · VERDICT

Our verdict

OP · Fredoline Eruo|VERIFIED JUN 18, 2026
8.3/10

What it is

The MI350X is AMD's air-cooled CDNA 4 datacenter GPU — same 288GB HBM3E and 8 TB/s as the liquid-cooled MI355X already in the catalog, but at a lower, air-coolable power envelope (1,000W class). The air-vs-liquid split matters operationally: the MI350X is the one that drops into standard air-cooled racks, which is what most non-hyperscale on-prem buyers actually run.

Relevance to local AI

AMD's 288GB-per-GPU on ROCm is the credible non-NVIDIA option for serving very large models on-prem, and the air-cooled MI350X is the realistic procurement target for an enterprise that can't deploy liquid cooling. The catch remains software: ROCm has closed much of the gap for inference (vLLM, SGLang support is solid) but still trails CUDA on the long tail. For an org standardizing on AMD Instinct for cost or supply reasons, this is the practical SKU.

Bottom line

The air-cooled, on-prem-friendly 288GB AMD datacenter GPU. Pairs with the MI355X row; choose AMD here for VRAM/cost on ROCm-supported inference, NVIDIA for maximum software compatibility. Confirm exact TDP against AMD's datasheet before relying on the power figure.

BLK · OVERVIEW

Overview

The air-coolable sibling of the listed MI355X — same CDNA 4 silicon, 288GB HBM3E, ~8 TB/s, at a lower (~1,000W-class) power profile. The variant most non-hyperscale on-prem deployments would actually buy. (TDP figure pending confirmation against AMD's official datasheet.)

Retailers we'd check:Amazon

Search-fallback link — editorial hasn't yet curated a retailer URL for this card.

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

BLK · SPECS

Specs

VRAM288 GB
Power draw (peak)1000 W
Released2025
Backends
ROCm

Models that fit

Open-weight models small enough to run on AMD Instinct MI350X with usable context.

all-MiniLM-L6-v2
0.022B · other
FLUX.1 [dev]
12B · other
Qwen 3 0.6B
0.6B · qwen
BGE Large EN v1.5
0.335B · other
Llama 4 Scout
109B · llama
Nomic Embed Text v1.5
0.137B · other
Kokoro 82M
0.082B · other
Llama 3.1 8B Instruct
8B · llama

Frequently asked

What models can AMD Instinct MI350X run?

With 288GB VRAM, the AMD Instinct MI350X runs 70B models in 4-bit quantization, plus everything smaller. See the model list below for tested combinations.

Does AMD Instinct MI350X support CUDA?

No — AMD Instinct MI350X is an AMD card. Use ROCm (Linux) or the Vulkan backend in llama.cpp instead. CUDA-only tools won't work.

Where next?

Buyer guides
  • Best GPU for local AI →
  • Best laptop for local AI →
  • Best Mac for local AI →
  • Best used GPU for local AI →
Troubleshooting
  • CUDA out of memory →
  • Ollama running slowly →
  • ROCm not detected →
  • Model keeps crashing →

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.

RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Compare alternatives

Hardware worth comparing

The closest alternatives by price, memory bandwidth, and form factor, plus a step up and down — so you can frame the buying decision against real options.

Closest matches
Similar price, bandwidth & form factor
  • NVIDIA B300 (Blackwell Ultra)
    nvidia · 288 GB VRAM
    9.2/10
  • NVIDIA B200
    nvidia · 192 GB VRAM
    10.0/10
  • AMD Instinct MI355X
    amd · 288 GB VRAM
    10.0/10
  • NVIDIA GB200 NVL72
    nvidia · 13824 GB VRAM
    10.0/10
  • NVIDIA H200
    nvidia · 141 GB VRAM
    10.0/10
  • Intel Gaudi 3
    intel · 128 GB VRAM
    8.2/10
Step up
More capable — more memory or a higher tier
  • NVIDIA GB200 NVL72
    nvidia · 13824 GB VRAM
    10.0/10
Step down
Lighter — cheaper or more constrained
  • NVIDIA B200
    nvidia · 192 GB VRAM
    10.0/10
  • Intel Gaudi 3
    intel · 128 GB VRAM
    8.2/10
  • AMD Instinct MI300X
    amd · 192 GB VRAM
    10.0/10