llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
71 vs 90
Hardware Fit
95 vs 96
Quality Score
60 vs 87
Hardware
llama3:latest qwen3-coder:30b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
llama3:latest qwen3-coder:30b
Tokens/sec22.3207.9
First chunkN/A513 ms
TTFT295 ms513 ms
Load time0.8 s4.9 s
Memory usage5.6 GB20.5 GB
Memory %18%43%
HW Fit Score Breakdown
llama3:latest
Speed
35/50
TTFT
30/20
Memory
30/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
llama3:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
qwen3-coder:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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