hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 23, 2026 · Apple M1 Pro
llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
66 vs 71
Hardware Fit
100 vs 95
Quality Score
52 vs 60
Hardware
hf.co/empero-ai/Qw… llama3:latest
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… llama3:latest
Tokens/sec40.422.3
First chunk93 msN/A
TTFT93 ms295 ms
Load time2.7 s0.8 s
Memory usage4.7 GB5.6 GB
Memory %30%18%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
llama3:latest
Speed
35/50
TTFT
30/20
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:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong 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