Back to leaderboard

qwen2.5-coder:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 26, 2026 · Apple M1 Pro

Global Score
68 vs 68
Hardware Fit
100 vs 86
Quality Score
54 vs 60

Hardware

qwen2.5-coder:1.5b qwen3.5:4b
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M1 Pro
Cores810
RAM15 GB16 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M1 Pro
OSPop 24.04 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen2.5-coder:1.5b qwen3.5:4b
Tokens/sec21.836.5
First chunk499 ms207 ms
TTFT499 ms6.6 s
Load time4.4 s3.2 s
Memory usage1.5 GB5.3 GB
Memory %10%33%

HW Fit Score Breakdown

qwen2.5-coder:1.5b

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

qwen3.5:4b

Speed
50/50
TTFT
7/20
Memory
29/30

Quality

qwen2.5-coder:1.5b

Reasoning
8/20
Coding
11/20
Instruction
13/20
Structured
11/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
12/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong 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