Back to leaderboard

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

qwen3.5:4b

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

Global Score
25 vs 81
Hardware Fit
46 vs 88
Quality Score
11 vs 76

Hardware

deepseek-r1:14b qwen3.5:4b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modeunknownbalanced

Performance

deepseek-r1:14b qwen3.5:4b
Tokens/sec10.816.6
TTFT30.0 s369 ms
Load time5.3 s1.5 s
Memory usage16.5 GB6.5 GB
Memory %52%20%

HW Fit Score Breakdown

deepseek-r1:14b

Speed
16/40
TTFT
0/30
Memory
30/30

qwen3.5:4b

Speed
28/40
TTFT
30/30
Memory
30/30

Quality

deepseek-r1:14b

Reasoning
1/20
Coding
0/20
Instruction
2/20
Structured
1/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

qwen3.5:4b

Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View deepseek-r1:14b details | View qwen3.5:4b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running