hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 26, 2026 · Apple M1 Pro
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
66 vs 86
Hardware Fit
100 vs 78
Quality Score
52 vs 89
Hardware
hf.co/empero-ai/Qw… Kimi-48B:48B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M1 ProIntel Core™ Ultra X7 358H
Cores1016
RAM16 GB64 GB
GPUApple M1 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… Kimi-48B:48B
Tokens/sec40.222.8
First chunk101 ms721 ms
TTFT101 ms721 ms
Load time2.6 s23.0 s
Memory usage4.7 GB25.5 GB
Memory %30%40%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
hf.co/empero-ai/Qwen3.8…
Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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