Back to leaderboard

phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score
28 vs 65
Hardware Fit
66 vs 96
Quality Score
11 vs 51

Hardware

phi-1_5 qwen3-4b-qwen3.6-p…
MachineLENOVO 20BUS00700Mac Studio
CPUIntel Core™ i5-5300UApple M2 Max
Cores412
RAM16 GB96 GB
GPUIntel(R) HD Graphics 5500Apple M2 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

phi-1_5 qwen3-4b-qwen3.6-p…
Tokens/sec6.999.6
First chunk3040 ms18 ms
TTFT3.0 s1.6 s
Load timeN/A4.8 s
Memory usage1.4 GB0.3 GB
Memory %9%0%

HW Fit Score Breakdown

phi-1_5

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

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
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

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

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