phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Nov 4, 2026 · Intel Core™ i7-9700
qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 25, 2026 · Apple M1 Pro
Global Score
75 vs 68
Hardware Fit
84 vs 91
Quality Score
71 vs 58
Hardware
phi4-mini:latest qwen3.5:4b-mlx
MachineVMware, Inc. VMware Virtual PlatformMacBook Pro
CPUIntel Core™ i7-9700Apple M1 Pro
Cores410
RAM16 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 24.04.5 LTSmacOS 26.6.2
Archx64arm64
Power Modeunknownbalanced
Performance
phi4-mini:latest qwen3.5:4b-mlx
Tokens/sec10.842.2
First chunk643 ms201 ms
TTFT643 ms4.4 s
Load time31.5 s0.0 s
Memory usage2.9 GB3.8 GB
Memory %19%24%
HW Fit Score Breakdown
phi4-mini:latest
Speed
34/50
TTFT
20/20
Memory
30/30
qwen3.5:4b-mlx
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5:4b-mlx
Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest