qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score

78 vs 64

Hardware Fit

59 vs 100

Quality Score

86 vs 48

Hardware

qwen2.5-coder:32b microsoft/phi-4-mi…

MachineNVIDIA NVIDIA_DGX_SparkMac mini

CPUCortex-X925Apple M4 Pro

Cores2014

RAM122 GB64 GB

GPUDevice 2e12Apple M4 Pro

OSUbuntu 24.04.4 LTSmacOS 15.7.4

Archarm64arm64

Power Modeperformancebalanced

Performance

qwen2.5-coder:32b microsoft/phi-4-mi…

Tokens/sec9.590.3

First chunk394 ms198 ms

TTFT395 ms198 ms

Load time72.1 sN/A

Memory usage26.5 GB2.0 GB

Memory %22%3%

HW Fit Score Breakdown

qwen2.5-coder:32b

Speed

9/50

TTFT

20/20

Memory

30/30

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

qwen2.5-coder:32b

Reasoning

14/20

Coding

19/20

Instruction

17/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

7/20

Instruction

7/20

Structured

7/15

Math

13/15

Multilingual

7/10

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

View qwen2.5-coder:32b details | View microsoft/phi-4-mi… 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