starcoder2:7b
OLLAMA GGUFstarcoder2 · 7B · Q4_0
Mar 2, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
35 vs 86
Hardware Fit
97 vs 78
Quality Score
8 vs 89
Hardware
starcoder2:7b Kimi-48B:48B
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
starcoder2:7b Kimi-48B:48B
Tokens/sec23.823.1
First chunkN/A752 ms
TTFT251 ms752 ms
Load time0.4 s22.2 s
Memory usage6.3 GB25.5 GB
Memory %20%40%
HW Fit Score Breakdown
starcoder2:7b
Speed
37/50
TTFT
30/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
starcoder2:7b
Reasoning
0/20
Coding
1/20
Instruction
4/20
Structured
2/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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