Qwen3-Coder-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ i7-14700F
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
91 vs 86
Hardware Fit
100 vs 78
Quality Score
87 vs 89
Hardware
Qwen3-Coder-30B:30b Kimi-48B:48B
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGMKtec NucBox EVO-T2S
CPUIntel Core™ i7-14700FIntel Core™ Ultra X7 358H
Cores2816
RAM128 GB64 GB
GPUNVIDIA GeForce RTX 5080Intel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
Qwen3-Coder-30B:30b Kimi-48B:48B
Tokens/sec74.022.8
First chunk381 ms721 ms
TTFT381 ms721 ms
Load time15.3 s23.0 s
Memory usage17.9 GB25.5 GB
Memory %14%40%
HW Fit Score Breakdown
Qwen3-Coder-30B:30b
Speed
50/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
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
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
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