Back to leaderboard

vicuna:13b

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score
59 vs 65
Hardware Fit
84 vs 99
Quality Score
48 vs 51

Hardware

vicuna:13b qwen3.5:0.8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

vicuna:13b qwen3.5:0.8b
Tokens/sec13.448.2
TTFT438 ms195 ms
Load time0.6 s1.0 s
Memory usage10.3 GB2.5 GB
Memory %32%8%

HW Fit Score Breakdown

vicuna:13b

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

qwen3.5:0.8b

Speed
40/40
TTFT
30/30
Memory
29/30

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

qwen3.5:0.8b

Reasoning
9/20
Coding
6/20
Instruction
11/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
View vicuna:13b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running