phi4-mini

LENOVO 20U30029MB (Intel Core™ i5-10210U)

15 GB · Pop 24.04 LTS

Tested on August 28, 2026

Top 88% Compare

Global Score

51 /100

Not Rec.

Hardware Fit

46/100

Quality

53/100

Get this model

🦙

Ollama

ollama pull phi4-mini

View on Ollama Library

ollama.com/library/phi4-mini

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: LENOVO 20U30029MB
CPU: Intel Core™ i5-10210U
Cores: 8 threads (4 cores)
Frequency: 1.6 GHz
RAM: 15 GB
GPU: CometLake-U GT2 [UHD Graphics]
OS: Pop 24.04 LTS
Arch: x64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 2.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 5.4 s
Time to first token How fast the model starts responding — lower is better: 5.4 s
Load time Time to load the model into memory before inference: 27.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 4.6 GB (30%)
Total tokens Total number of tokens generated across all benchmark prompts: 1255

Score breakdown

Speed

6/50

Time to first token

10/20

Memory

30/30

Quality

Reasoning

11/20

Coding

9/20

Instruction following

6/20

Structured output

12/15

Math

5/15

Multilingual

10/10

Category levels

Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.1
Model format: GGUF
Hardware profile: ENTRY
Result hash: 198321013c6791c2efa219d2891c0d8772b450841ff5fbea740aabe324738143

Interpretation

Hardware fit: 46/100. Overall suitability: NOT RECOMMENDED (Global 51/100). Category profile: Reasoning: Adequate, Coding: Weak, Instruction Following: Weak, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Warnings

CPU appears throttled (0.8 GHz current vs 1.6 GHz nominal, 50%).
Running on battery power — performance may be reduced.

Disqualifiers

Token speed too low: 2.6 tok/s (minimum: 3 tok/s for ENTRY profile)

Bench Environment

Thermal: nominal Power: Battery CPU load: avg 59% (peak 75%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest