Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
59 vs 88
Hardware Fit
65 vs 85
Quality Score
57 vs 89

Hardware

qwen3.5-9b-mlx huihui-qwen3.6-35b…
MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4AMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM24 GB47 GB
GPUApple M4AD106 [GeForce RTX 4060 Ti]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5-9b-mlx huihui-qwen3.6-35b…
Tokens/sec14.337.7
First chunk24 ms18 ms
TTFT13.4 s2.9 s
Load time13.3 sN/A
Memory usage2.5 GB26.1 GB
Memory %10%56%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
32/50
TTFT
3/20
Memory
30/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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