maternion/ling-3.0-tiny:8b
OLLAMA GGUFbailingmoe3 · 7.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
qwen3-30b-a3b-t16-c32k-instruct:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
88 vs 94
Hardware Fit
98 vs 100
Quality Score
83 vs 91
Hardware
maternion/ling-3.0… qwen3-30b-a3b-t16-…
MachineMacBook ProDell Inc. Precision Tower 7910
CPUApple M1 ProIntel Xeon® E5-2637 v3
Cores1016
RAM16 GB96 GB
GPUApple M1 ProNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSmacOS 26.6.2Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
maternion/ling-3.0… qwen3-30b-a3b-t16-…
Tokens/sec73.0116.0
First chunk175 ms575 ms
TTFT175 ms575 ms
Load time3.2 s10.2 s
Memory usage5.9 GB21.0 GB
Memory %37%22%
HW Fit Score Breakdown
maternion/ling-3.0-tiny…
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3-30b-a3b-t16-c32k-…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
maternion/ling-3.0-tiny…
Reasoning
16/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3-30b-a3b-t16-c32k-…
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
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