mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
Global Score
73 vs 89
Hardware Fit
100 vs 96
Quality Score
62 vs 86
Hardware
mistral:latest qwen3-coder:30b
MachineMicro-Star International Co., Ltd. MS-7B79MacBook Pro
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M4 Max
Cores1216
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Apple M4 Max
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.5.1
Archx64arm64
Power Modebalancedbalanced
Performance
mistral:latest qwen3-coder:30b
Tokens/sec31.789.9
First chunk102 ms188 ms
TTFT102 ms188 ms
Load time14.3 s4.0 s
Memory usage4.8 GB30.2 GB
Memory %30%47%
HW Fit Score Breakdown
mistral:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
qwen3-coder:30b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate 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