qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 18, 2026 · Apple M4 Max
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
81 vs 86
Hardware Fit
68 vs 78
Quality Score
87 vs 89
Hardware
qwen/qwen3.8-27b Kimi-48B:48B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M4 MaxIntel Core™ Ultra X7 358H
Cores1616
RAM128 GB64 GB
GPUApple M4 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen/qwen3.8-27b Kimi-48B:48B
Tokens/sec16.423.1
First chunk5 ms752 ms
TTFT742 ms752 ms
Load timeN/A22.2 s
Memory usage38.5 GB25.5 GB
Memory %30%40%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
18/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
qwen/qwen3.8-27b
Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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