Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Aug 19, 2026 · Apple M4 Max
Global Score
86 vs 83
Hardware Fit
78 vs 68
Quality Score
89 vs 90
Hardware
Kimi-48B:48B qwen/qwen3.8-27b
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M4 Max
Cores1616
RAM64 GB128 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B qwen/qwen3.8-27b
Tokens/sec22.827.6
First chunk721 ms10 ms
TTFT721 ms4.6 s
Load time23.0 sN/A
Memory usage25.5 GB21.0 GB
Memory %40%16%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
qwen/qwen3.8-27b
Speed
32/50
TTFT
6/20
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
qwen/qwen3.8-27b
Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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