qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
76 vs 86
Hardware Fit
51 vs 78
Quality Score
87 vs 89
Hardware
qwen3-coder:latest Kimi-48B:48B
MachineDell Inc. Inspiron 15 3530GMKtec NucBox EVO-T2S
CPUIntel Gen Intel® Core™ i7-1355UIntel Core™ Ultra X7 358H
Cores1216
RAM31 GB64 GB
GPURaptor Lake-P [Iris Xe Graphics]Intel(R) Arc(TM) B390 GPU
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3-coder:latest Kimi-48B:48B
Tokens/sec7.623.1
First chunk2037 ms752 ms
TTFT2.0 s752 ms
Load time8.7 s22.2 s
Memory usage18.9 GB25.5 GB
Memory %61%40%
HW Fit Score Breakdown
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
qwen3-coder:latest
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