NPUIntel

Intel Core Ultra 7 258V (Lunar Lake)

Curated Aggregate·2025-01-084 workloads · 5 records
MyAI RatingNot scoredInsufficient comparison evidence

VRAM

0 GB

TDP

17 W

MSRP

$1.3k

Perf/W

1.29 tok/s/W

Cost/1K tok

$0.62/M

Tested

2025-01-08

Quick answer

How fast is Intel Core Ultra 7 258V (Lunar Lake) for local AI workloads?

Intel Core Ultra 7 258V (Lunar Lake) has a source-attributed result of 5.5 tok/s on Llama 3 8B Q4 (batch 1, 2048-token context, INT4; runtime not documented). This is a reference report, not an independently verified lab result. A 70B Q4_K_M artifact needs roughly 40GB for weights alone; smaller memory configurations require explicit offload or model splitting and do not establish full-GPU residency.

Source: MyAIHardware benchmark database (bench-lunar-lake-l3-8b)As of 2025-03-04

Verdict

Intel Core Ultra 7 258V (Lunar Lake) with 0GB VRAM at 17W TDP, scored across 4 workloads with 5 benchmark records.

Reference workload

Llama 3 8B Q4

5.5 tok/s

Quantization

INT4

2K context · batch 1

LLM Inference Performance

06121824Phi-3 MiniLlama 3 8BQ4Mistral 7B

Benchmarks (4 workloads)

WorkloadScoreQuantContextσStatusTested
Phi-3 Mini

llm

22.0tok/sINT42K, Curated Aggregate2025-01-08
Whisper transcription

audio

4.2x RTINT8, , Curated Aggregate2025-02-04
Llama 3 8B Q4

llm

5.5tok/sINT42K, Curated Aggregate2025-03-04
Mistral 7B

llm

13.0tok/sQ4_K_M4K, Curated Aggregate2024-10-08

MyAI Score: not scored

There is insufficient comparable evidence to score Intel Core Ultra 7 258V (Lunar Lake). A score needs results for multiple devices with matching workload, runtime version, quantization, context and batch size.

Workload Fit

Planning estimates for 0GB: weights plus at least 2GB or 10% overhead. Actual KV cache depends on model, context and cache format; confirm the artifact before buying.

Q4
Q8
FP16
7-8B
Won't fit
Won't fit
Won't fit
13-14B
Won't fit
Won't fit
Won't fit
32B
Won't fit
Won't fit
Won't fit
70B
Won't fit
Won't fit
Won't fit
Reported batch-one examples
Llama 3 8B Q46 tok/s
Whisper transcription4 x RT
Phi-3 Mini22 tok/s

Source

Hybrid NPU+iGPU via OpenVINO.

View sourceHow we benchmark →

Public Trust Layer

Trust score

6/10

MyAI rating

Not scored

Runs

Not documented

Freshness

Stale

Source-linked row with explicit verification status.

Record date: 2025-03-04; 554 days old.

Open primary source

Best place to start

Where to buy

Search first

Retailer we'd check first

Amazon search

For mainstream AI hardware, Amazon usually updates street pricing, seller availability, and shipping speed faster than most comparison sites.

Search Amazon listings
  • +Use $1.3k as your price anchor unless the part is clearly supply-constrained or newly launched.
  • +Check the exact cooler, board partner, or memory configuration before buying. The silicon may match, but noise and thermals do not.
  • +If the Amazon price looks inflated, wait or compare against recent street pricing rather than paying a panic premium.

There is insufficient comparable evidence for a purchase recommendation. Check model fit, software support and a current seller quote.

Affiliate note: we do not have a device-level ASIN yet, so this opens tagged Amazon search results for the exact product name.

Same Tier

Intel Core Ultra 9 285K NPU
0GB
Intel Core Ultra 9 288V (Lunar Lake) NPU
0GB
AMD Ryzen AI 9 HX 370 NPU
0GB
Qualcomm Snapdragon X Elite (X1E-84-100)
0GB
AMD Ryzen AI 9 365 NPU
0GB
AMD Ryzen AI Max+ 395 (Strix Halo, 96GB)
96GB