Back to leaderboard

mistral-nemo:12b

llama · 12.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

vicuna:13b

llama · 13B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
73 vs 62
Hardware Fit
86 vs 84
Quality Score
65 vs 48

Hardware

mistral-nemo:12b vicuna:13b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

mistral-nemo:12b vicuna:13b
Tokens/sec14.613.4
TTFT371 ms438 ms
Load time1.0 s0.6 s
Memory usage13.3 GB10.3 GB
Memory %42%32%

HW Fit Score Breakdown

mistral-nemo:12b

Speed
26/40
TTFT
30/30
Memory
30/30

vicuna:13b

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

Quality

mistral-nemo:12b

Reasoning
12/20
Coding
13/20
Instruction
11/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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
View mistral-nemo:12b details | View vicuna:13b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running