Back to leaderboard

qwen3.5-2b-mlx

qwen3_5 · 2B · 8bit

Marginal

Mar 3, 2026 · Apple M4

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score
49 vs 22
Hardware Fit
83 vs 50
Quality Score
35 vs 10

Hardware

qwen3.5-2b-mlx deepseek-r1:14b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx deepseek-r1:14b
Tokens/sec18.611.4
TTFT2.9 s30.0 s
Load time0.0 s1.0 s
Memory usage0.0 GB16.5 GB
Memory %0%52%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
31/40
TTFT
22/30
Memory
30/30

deepseek-r1:14b

Speed
20/40
TTFT
0/30
Memory
30/30

Quality

qwen3.5-2b-mlx

Reasoning
0/20
Coding
9/20
Instruction
10/20
Structured
4/15
Math
3/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Strong

deepseek-r1:14b

Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
View qwen3.5-2b-mlx details | View deepseek-r1:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running