phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
85 vs 66
Hardware Fit
100 vs 91
Quality Score
79 vs 55
Hardware
phi4:latest qwen3.8-27b-mlx
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Pro
CPUIntel Core™ i5-14400FApple M5 Max
Cores1618
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 5060 TiApple M5 Max
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
phi4:latest qwen3.8-27b-mlx
Tokens/sec38.333.2
First chunk72 ms7 ms
TTFT72 ms311 ms
Load time6.2 sN/A
Memory usage9.1 GB0.5 GB
Memory %29%1%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
phi4:latest
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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