Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
86 vs 76
Hardware Fit
78 vs 46
Quality Score
89 vs 89
Hardware
Kimi-48B:48B gemma4:31b
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M4 Max
Cores1616
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3.1
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B gemma4:31b
Tokens/sec23.122.4
First chunk752 ms565 ms
TTFT752 ms30.0 s
Load time22.2 s6.9 s
Memory usage25.5 GB43.9 GB
Memory %40%69%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
Quality
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
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
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