Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
86 vs 80
Hardware Fit
78 vs 100
Quality Score
89 vs 71
Hardware
Kimi-48B:48B mlx-community/gemm…
MachineGMKtec NucBox EVO-T2SMacBook Air
CPUIntel Core™ Ultra X7 358HApple M4
Cores1610
RAM64 GB32 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B mlx-community/gemm…
Tokens/sec22.843.2
First chunk721 ms428 ms
TTFT721 ms428 ms
Load time23.0 sN/A
Memory usage25.5 GB1.3 GB
Memory %40%4%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
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
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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