Back to leaderboard

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M

OLLAMA GGUF

qwen35 · 4.33B · unknown

Good

Aug 28, 2026 · Apple M4

Global Score
66 vs 66
Hardware Fit
100 vs 100
Quality Score
51 vs 52

Hardware

deepseek-r1:1.5b hf.co/empero-ai/Qw…
MachineMacBook AirMacBook Pro
CPUApple M4Apple M4
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-r1:1.5b hf.co/empero-ai/Qw…
Tokens/sec85.426.5
First chunk115 ms447 ms
TTFT115 ms447 ms
Load time0.5 s3.3 s
Memory usage2.6 GB4.8 GB
Memory %8%30%

HW Fit Score Breakdown

deepseek-r1:1.5b

Speed
50/50
TTFT
20/20
Memory
30/30

hf.co/empero-ai/Qwen3.8…

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

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

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest