Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

qwen3.5-9b

LM-STUDIO GGUF

qwen35 · 9B · Q4_K_S

Not Rec.

Mar 14, 2026 · Apple M4

Global Score
62 vs 72
Hardware Fit
35 vs 51
Quality Score
73 vs 81

Hardware

qwen3.5-4b-mlx qwen3.5-9b
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

qwen3.5-4b-mlx qwen3.5-9b
Tokens/sec0.014.4
First chunk5548 ms4 ms
TTFT5.5 s824 ms
Load timeN/AN/A
Memory usage2.9 GB48.3 GB
Memory %5%151%

HW Fit Score Breakdown

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

qwen3.5-9b

Speed
31/50
TTFT
20/20
Memory
0/30

Quality

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

qwen3.5-9b

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