qwen2.5-coder:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Nov 13, 2026 · Intel Core™ i5-4590T
qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
Global Score
59 vs 70
Hardware Fit
100 vs 93
Quality Score
41 vs 60
Hardware
qwen2.5-coder:0.5b qwen3.5-2b-mlx
MachineFUJITSU ESPRIMO Q920MacBook Air
CPUIntel Core™ i5-4590TApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterApple M4
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5-coder:0.5b qwen3.5-2b-mlx
Tokens/sec43.732.9
First chunk290 ms3096 ms
TTFT290 ms3.1 s
Load time1.4 sN/A
Memory usage0.9 GB2.5 GB
Memory %6%8%
HW Fit Score Breakdown
qwen2.5-coder:0.5b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
Quality
qwen2.5-coder:0.5b
Reasoning
7/20
Coding
8/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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