Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

yi-coder:9b

OLLAMA GGUF

llama · 8.8B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
62 vs 70
Hardware Fit
35 vs 89
Quality Score
73 vs 62

Hardware

qwen3.5-4b-mlx yi-coder: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 yi-coder:9b
Tokens/sec0.019.4
First chunk5548 ms287 ms
TTFT5.5 s287 ms
Load timeN/A0.7 s
Memory usage2.9 GB9.6 GB
Memory %5%30%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

yi-coder:9b

Speed
39/50
TTFT
20/20
Memory
30/30

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

yi-coder:9b

Reasoning
12/20
Coding
16/20
Instruction
13/20
Structured
7/15
Math
7/15
Multilingual
7/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Weak Math: Weak Multilingual: Adequate
View qwen3.5-4b-mlx details | View yi-coder:9b 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