phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 18, 2026 · Apple M4 Max
Global Score
85 vs 81
Hardware Fit
100 vs 68
Quality Score
79 vs 87
Hardware
phi4:latest qwen/qwen3.8-27b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Pro
CPUIntel Core™ i5-14400FApple M4 Max
Cores1616
RAM32 GB128 GB
GPUNVIDIA GeForce RTX 5060 TiApple M4 Max
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
phi4:latest qwen/qwen3.8-27b
Tokens/sec38.316.4
First chunk72 ms5 ms
TTFT72 ms742 ms
Load time6.2 sN/A
Memory usage9.1 GB38.5 GB
Memory %29%30%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3.8-27b
Speed
18/50
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
qwen/qwen3.8-27b
Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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