Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

qwen3.5-4b-super-coder

LM-STUDIO GGUF

qwen35 · 4B · Q4_0

Excellent

Oct 24, 2026 · Intel Core™ i3-9100F

Global Score
77 vs 83
Hardware Fit
67 vs 96
Quality Score
81 vs 77

Hardware

qwen3.5-9b-mlx qwen3.5-4b-super-c…
MachineMac miniGigabyte Technology Co., Ltd. H310M S2 2.0
CPUApple M4 ProIntel Core™ i3-9100F
Cores144
RAM64 GB16 GB
GPUApple M4 ProVirtual Desktop Monitor, NVIDIA GeForce GTX 1650
OSmacOS 15.7.4Майкрософт Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx qwen3.5-4b-super-c…
Tokens/sec20.315.3
First chunk4216 ms33 ms
TTFT4.2 s686 ms
Load timeN/AN/A
Memory usage5.6 GB3.6 GB
Memory %9%22%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

qwen3.5-4b-super-coder

Speed
46/50
TTFT
20/20
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

qwen3.5-4b-super-coder

Reasoning
16/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-9b-mlx details | View qwen3.5-4b-super-c… 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