qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Mar 2, 2026 · Apple M4
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 29, 2026 · Intel Xeon® E5-2637 v3
Global Score
61 vs 83
Hardware Fit
100 vs 66
Quality Score
44 vs 90
Hardware
qwen3:0.6b qwen3:30b-a3b-inst…
MachineMacBook AirDell Inc. Precision Tower 7910
CPUApple M4Intel Xeon® E5-2637 v3
Cores1016
RAM32 GB96 GB
GPUApple M4NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3:0.6b qwen3:30b-a3b-inst…
Tokens/sec144.317.7
First chunkN/A1244 ms
TTFT81 ms1.2 s
Load time0.9 s20.5 s
Memory usage4.1 GB20.6 GB
Memory %13%21%
HW Fit Score Breakdown
qwen3:0.6b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3:30b-a3b-instruct-…
Speed
19/50
TTFT
17/20
Memory
30/30
Quality
qwen3:0.6b
Reasoning
6/20
Coding
4/20
Instruction
10/20
Structured
13/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Weak
qwen3:30b-a3b-instruct-…
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
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