Back to leaderboard

phi4-mini

OLLAMA GGUF
Not Rec.

Aug 28, 2026 · Intel Core™ i5-10210U

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
51 vs 75
Hardware Fit
46 vs 50
Quality Score
53 vs 86

Hardware

phi4-mini qwen2.5:72b
MachineLENOVO 20U30029MBNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-10210UCortex-X925
Cores820
RAM15 GB122 GB
GPUCometLake-U GT2 [UHD Graphics]Device 2e12
OSPop 24.04 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance

Performance

phi4-mini qwen2.5:72b
Tokens/sec2.64.4
First chunk5406 ms529 ms
TTFT5.4 s529 ms
Load time27.4 s49.7 s
Memory usage4.6 GB54.0 GB
Memory %30%44%

HW Fit Score Breakdown

phi4-mini

Speed
6/50
TTFT
10/20
Memory
30/30

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

Quality

phi4-mini

Reasoning
11/20
Coding
9/20
Instruction
6/20
Structured
12/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View phi4-mini details | View qwen2.5:72b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest