RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
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
  1. >
  2. Home
  3. /Hardware
  4. /Intel Core Ultra 300 (Panther Lake)
UNIT · INTEL · PC-NPU
32 GB UNIFIEDpc-npu·Reviewed June 2026

Intel Core Ultra 300 (Panther Lake)

INTC · HARDWARE
Intel Core Ultra 300 (Panther Lake)

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

Intel's current-gen AI-PC platform (launched Jan 2026, Intel 18A node), succeeding Lunar Lake. NPU5 delivers ~50 TOPS (clears the 40-TOPS Copilot+ bar); combined platform ~180 TOPS with the Xe3 (Celestial) iGPU.

Released 2026
RUNLOCALAI SCORE
See full leaderboard →
175/ 1000
DD-tier
Estimated
Throughput
0/ 500
VRAM-fit
170/ 200
Ecosystem
80/ 200
Efficiency
0/ 100

Sub-scores sum to 250 / 1000. Headline = 250 × 0.70 (Estimated-confidence discount) = 175. 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 →

Insufficient data — VRAM ?GB, bandwidth ? GB/s.

WORKLOAD FIT
Try other hardware →

Plain-English: Doesn't fit modern chat models usefully.

7B chat△
Marginal
14B chat△
Marginal
32B chat△
Marginal
70B chat✗
Doesn't fit
Coding agent△
Marginal
Vision (≤8B VLM)△
Marginal
Long context (32K)△
Marginal
✓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 9, 2026
6.8/10

What it is

Panther Lake (Core Ultra 300) is Intel's 2026 AI-PC platform on the new 18A node, succeeding the Lunar Lake chip already in the catalog. Its NPU5 hits ~50 TOPS — past the 40-TOPS Copilot+ threshold — and the platform total reaches ~180 TOPS once you add the Xe3 'Celestial' iGPU.

Relevance to local AI

Like all AI-PC NPUs, the honest framing matters: 50 TOPS is meaningful for Windows Studio Effects, background AI features, and small quantized models via OpenVINO, but it is not a substitute for a GPU or unified-memory box for running 7B+ LLMs at speed. The iGPU + NPU combo can run small models locally and is genuinely more efficient than prior gen, but local-LLM tooling for NPUs is still thin. Intel's own messaging is more about efficiency and the 18A node than a raw AI-perf leap over Lunar Lake. Useful as the current-gen reference for 'what's in a 2026 AI laptop,' not as a serious local-LLM engine.

Bottom line

The current-gen Intel AI-PC chip — relevant for efficient on-device AI features and light local models, but NPUs remain a complement to, not a replacement for, GPU/unified-memory hardware for real local LLM work.

BLK · OVERVIEW

Overview

Intel's current-gen AI-PC platform (launched Jan 2026, Intel 18A node), succeeding Lunar Lake. NPU5 delivers ~50 TOPS (clears the 40-TOPS Copilot+ bar); combined platform ~180 TOPS with the Xe3 (Celestial) iGPU.

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

System RAM (typical)32 GB
Power draw (peak)28 W
Released2026
Backends
Vulkan

Models that fit

Open-weight models small enough to run on Intel Core Ultra 300 (Panther Lake) 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
Nomic Embed Text v1.5
0.137B · other
Kokoro 82M
0.082B · other
Llama 3.1 8B Instruct
8B · llama
XTTS v2
0.46B · other

Frequently asked

Does Intel Core Ultra 300 (Panther Lake) support CUDA?

Intel Core Ultra 300 (Panther Lake) does not support CUDA. Use Vulkan-compatible tools (llama.cpp Vulkan backend) or check vendor-specific runtimes.

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.

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
  • AMD Ryzen AI 9 HX 370 (Strix Point)
    amd · 90 GB/s
    3.9/10
  • Qualcomm Snapdragon X2 Elite
    qualcomm · pc-npu
    6.9/10
  • Apple M3 Ultra
    apple · 800 GB/s
    10.0/10
  • Apple M4 Pro
    apple · 273 GB/s
    10.0/10
  • Apple M4 Ultra
    apple · 1100 GB/s
    10.0/10
  • Qualcomm Snapdragon X Elite
    qualcomm · high
    7.3/10
Step up
More capable — more memory or a higher tier
  • Apple M3 Ultra
    apple · 800 GB/s
    10.0/10
  • Apple M4 Pro
    apple · 273 GB/s
    10.0/10
  • Apple M4 Ultra
    apple · 1100 GB/s
    10.0/10
Step down
Lighter — cheaper or more constrained
No verdicted hardware in the next tier down yet.