Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

vicuna:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score
77 vs 59
Hardware Fit
67 vs 84
Quality Score
81 vs 48

Hardware

qwen3.5-9b-mlx vicuna:13b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx vicuna:13b
Tokens/sec20.313.4
First chunk4216 msN/A
TTFT4.2 s438 ms
Load timeN/A0.6 s
Memory usage5.6 GB10.3 GB
Memory %9%32%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

vicuna:13b

Speed
24/50
TTFT
30/20
Memory
30/30

Quality

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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 qwen3.5-9b-mlx details | View vicuna:13b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest