Back to leaderboard

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
73 vs 71
Hardware Fit
96 vs 88
Quality Score
63 vs 63

Hardware

mistral:latest qwen3.5-4b-mlx
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

mistral:latest qwen3.5-4b-mlx
Tokens/sec22.523.1
First chunkN/A3279 ms
TTFT257 ms3.3 s
Load time0.6 sN/A
Memory usage10.1 GB2.9 GB
Memory %32%9%

HW Fit Score Breakdown

mistral:latest

Speed
36/50
TTFT
30/20
Memory
30/30

qwen3.5-4b-mlx

Speed
45/50
TTFT
13/20
Memory
30/30

Quality

mistral:latest

Reasoning
8/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
5/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

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