Back to leaderboard

yi:6b

llama · 6B · Q4_0

Good

Mar 1, 2026 · Apple M4

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score
77 vs 22
Hardware Fit
100 vs 50
Quality Score
67 vs 10

Hardware

yi:6b 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

yi:6b deepseek-r1:14b
Tokens/sec27.611.4
TTFT210 ms30.0 s
Load time0.4 s1.0 s
Memory usage3.6 GB16.5 GB
Memory %11%52%

HW Fit Score Breakdown

yi:6b

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

deepseek-r1:14b

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

Quality

yi:6b

Reasoning
11/20
Coding
12/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate

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 yi:6b details | View deepseek-r1:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running