qwen/qwen3-coder-30b
LM-STUDIO GGUFqwen3moe · 30B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
gpt-oss-20b
LM-STUDIO GGUFMar 6, 2026 · Apple M4 Pro
Global Score
85 vs 95
Hardware Fit
79 vs 94
Quality Score
88 vs 95
Hardware
qwen/qwen3-coder-30b gpt-oss-20b
MachineGMKtec EVO-X3Mac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3214
RAM120 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3-coder-30b gpt-oss-20b
Tokens/sec42.3118.2
First chunk10 ms471 ms
TTFT707 ms2.2 s
Load time167.7 sN/A
Memory usage70.3 GB11.3 GB
Memory %59%18%
HW Fit Score Breakdown
qwen/qwen3-coder-30b
Speed
40/50
TTFT
18/20
Memory
21/30
gpt-oss-20b
Speed
50/50
TTFT
14/20
Memory
30/30
Quality
qwen/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: Strong Multilingual: Strong
gpt-oss-20b
Reasoning
19/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
15/15
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