qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
80 vs 53
Hardware Fit
60 vs 99
Quality Score
88 vs 33
Hardware
qwen3-coder:30b mlx-community/Nanb…
MachineASUSMacBook Air
CPUIntel Gen Intel® Core™ i7-12700KApple M4
Cores2010
RAM96 GB32 GB
GPUParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060Apple M4
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3-coder:30b mlx-community/Nanb…
Tokens/sec14.725.4
First chunk796 ms266 ms
TTFT796 ms266 ms
Load time0.2 sN/A
Memory usage17.9 GB0.0 GB
Memory %19%0%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
Memory
30/30
Quality
qwen3-coder:30b
Reasoning
17/20
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
mlx-community/Nanbeige4…
Reasoning
10/20
Coding
7/20
Instruction
1/20
Structured
1/15
Math
11/15
Multilingual
3/10
Reasoning: Adequate Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Weak
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