Back to leaderboard

phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5-27b

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
28 vs 26
Hardware Fit
66 vs 63
Quality Score
11 vs 10

Hardware

phi-1_5 qwen3.5-27b
MachineLENOVO 20BUS00700Mac mini
CPUIntel Core™ i5-5300UApple M4 Pro
Cores414
RAM16 GB64 GB
GPUIntel(R) HD Graphics 5500Apple M4 Pro
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

phi-1_5 qwen3.5-27b
Tokens/sec6.99.5
First chunk3040 ms1099 ms
TTFT3.0 s1.1 s
Load timeN/AN/A
Memory usage1.4 GB16.3 GB
Memory %9%25%

HW Fit Score Breakdown

phi-1_5

Speed
24/50
TTFT
16/20
Memory
26/30

qwen3.5-27b

Speed
13/50
TTFT
20/20
Memory
30/30

Quality

phi-1_5

Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.5-27b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
7/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

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