hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
66 vs 74
Hardware Fit
100 vs 98
Quality Score
52 vs 63
Hardware
hf.co/empero-ai/Qw… phi4-mini:latest
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M1 ProIntegrated / Unknown
OSmacOS 26.6.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… phi4-mini:latest
Tokens/sec40.218.4
First chunk325 ms1078 ms
TTFT325 ms1.1 s
Load time3.1 s6.4 s
Memory usage4.7 GB2.9 GB
Memory %30%39%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
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
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate 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