qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

llama2:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

75 vs 56

Hardware Fit

50 vs 84

Quality Score

86 vs 44

Hardware

qwen2.5:72b llama2:13b

MachineNVIDIA NVIDIA_DGX_SparkMacBook Air

CPUCortex-X925Apple M4

Cores2010

RAM122 GB32 GB

GPUDevice 2e12Apple M4

OSUbuntu 24.04.4 LTSmacOS 26.3

Archarm64arm64

Power Modeperformancebalanced

Performance

qwen2.5:72b llama2:13b

Tokens/sec4.413.5

First chunk529 msN/A

TTFT529 ms415 ms

Load time49.7 s0.6 s

Memory usage54.0 GB10.3 GB

Memory %44%32%

HW Fit Score Breakdown

qwen2.5:72b

Speed

4/50

TTFT

20/20

Memory

26/30

llama2:13b

Speed

24/50

TTFT

30/20

Memory

30/30

Quality

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

llama2:13b

Reasoning

9/20

Coding

3/20

Instruction

13/20

Structured

7/15

Math

3/15

Multilingual

9/10

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

View qwen2.5:72b details | View llama2:13b 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