qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Oct 11, 2026 · AMD Ryzen 5 5500
gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
74 vs 76
Hardware Fit
100 vs 51
Quality Score
63 vs 87
Hardware
qwen3:0.6b gemma-3-27b-it-qat
MachineMicrosoft WSLMac mini
CPUAMD Ryzen 5 5500Apple M4 Pro
Cores1214
RAM8 GB64 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 26.04.1 LTSmacOS 15.7.4
Archx64arm64
Power Modeunknownbalanced
Performance
qwen3:0.6b gemma-3-27b-it-qat
Tokens/sec249.58.9
First chunk80 ms3976 ms
TTFT659 ms4.0 s
Load time6.3 sN/A
Memory usage0.9 GB15.7 GB
Memory %11%25%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
20/20
Memory
30/30
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
Quality
qwen3:0.6b
Reasoning
13/20
Coding
6/20
Instruction
12/20
Structured
13/15
Math
12/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
gemma-3-27b-it-qat
Reasoning
16/20
Coding
18/20
Instruction
17/20
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