hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 25, 2026 · Apple M1 Pro
gemma4:e4b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
76 vs 90
Hardware Fit
100 vs 86
Quality Score
66 vs 92
Hardware
hf.co/empero-ai/Qw… gemma4:e4b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M1 ProApple M1 Pro
OSmacOS 26.6.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… gemma4:e4b-mlx
Tokens/sec40.341.8
First chunk101 ms359 ms
TTFT101 ms4.2 s
Load time2.7 s5.1 s
Memory usage4.5 GB7.9 GB
Memory %28%49%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
11/20
Memory
25/30
Quality
hf.co/empero-ai/Qwen3.8…
Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:e4b-mlx
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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