hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
66 vs 63
Hardware Fit
100 vs 100
Quality Score
52 vs 47
Hardware
hf.co/empero-ai/Qw… llama3.2:1b
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… llama3.2:1b
Tokens/sec40.240.2
First chunk325 ms1087 ms
TTFT325 ms1.1 s
Load time3.1 s6.2 s
Memory usage4.7 GB1.4 GB
Memory %30%19%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
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
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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