hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M
OLLAMA GGUFqwen35 · 4.33B · unknown
Aug 28, 2026 · Apple M4
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
66 vs 66
Hardware Fit
100 vs 100
Quality Score
52 vs 51
Hardware
hf.co/empero-ai/Qw… deepseek-r1:1.5b
MachineMacBook ProMacBook Air
CPUApple M4Apple M4
Cores1010
RAM16 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… deepseek-r1:1.5b
Tokens/sec26.585.4
First chunk447 ms115 ms
TTFT447 ms115 ms
Load time3.3 s0.5 s
Memory usage4.8 GB2.6 GB
Memory %30%8%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:1.5b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
hf.co/empero-ai/Qwen3.8…
Reasoning
18/20
Coding
14/20
Instruction
4/20
Structured
1/15
Math
15/15
Multilingual
0/10
Reasoning: Strong Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
deepseek-r1:1.5b
Reasoning
14/20
Coding
4/20
Instruction
8/20
Structured
6/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong 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