qwen2.5-coder:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Nov 13, 2026 · Intel Core™ i5-4590T
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
Global Score
59 vs 95
Hardware Fit
100 vs 94
Quality Score
41 vs 96
Hardware
qwen2.5-coder:0.5b qwen3-30b-a3b-thin…
MachineFUJITSU ESPRIMO Q920Mac Studio
CPUIntel Core™ i5-4590TApple M2 Max
Cores412
RAM16 GB96 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterApple M2 Max
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5-coder:0.5b qwen3-30b-a3b-thin…
Tokens/sec43.780.4
First chunk290 ms46 ms
TTFT290 ms1.8 s
Load time1.4 sN/A
Memory usage0.9 GB21.2 GB
Memory %6%22%
HW Fit Score Breakdown
qwen2.5-coder:0.5b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
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
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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