Back to leaderboard

vicuna:13b

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score
59 vs 22
Hardware Fit
84 vs 50
Quality Score
48 vs 10

Hardware

vicuna:13b 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

vicuna:13b deepseek-r1:14b
Tokens/sec13.411.4
TTFT438 ms30.0 s
Load time0.6 s1.0 s
Memory usage10.3 GB16.5 GB
Memory %32%52%

HW Fit Score Breakdown

vicuna:13b

Speed
24/40
TTFT
30/30
Memory
30/30

deepseek-r1:14b

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

Quality

vicuna:13b

Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong 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 vicuna:13b details | View deepseek-r1:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running