Qwen3-Coder-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.5-9b
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 3, 2026 · Apple M4
Global Score
91 vs 81
Hardware Fit
100 vs 84
Quality Score
87 vs 79
Hardware
Qwen3-Coder-30B:30b qwen3.5-9b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Air
CPUIntel Core™ i7-14700FApple M4
Cores2810
RAM128 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M4
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
Qwen3-Coder-30B:30b qwen3.5-9b
Tokens/sec74.020.4
First chunk381 ms3034 ms
TTFT381 ms3.0 s
Load time15.3 sN/A
Memory usage17.9 GB5.6 GB
Memory %14%17%
HW Fit Score Breakdown
Qwen3-Coder-30B:30b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-9b
Speed
41/50
TTFT
14/20
Memory
29/30
Quality
Qwen3-Coder-30B:30b
Reasoning
16/20
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
qwen3.5-9b
Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate 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