deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 6, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
77 vs 86
Hardware Fit
94 vs 78
Quality Score
70 vs 89
Hardware
deepseek-r1:7b 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
deepseek-r1:7b Kimi-48B:48B
Tokens/sec22.223.1
First chunk285 ms752 ms
TTFT285 ms752 ms
Load time0.8 s22.2 s
Memory usage7.6 GB25.5 GB
Memory %24%40%
HW Fit Score Breakdown
deepseek-r1:7b
Speed
44/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
deepseek-r1:7b
Reasoning
14/20
Coding
12/20
Instruction
10/20
Structured
12/15
Math
15/15
Multilingual
7/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
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