Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
77 vs 92
Hardware Fit
67 vs 87
Quality Score
81 vs 94

Hardware

qwen3.5-9b-mlx qwen3.6-35b-a3b-cl…
MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4 ProAMD Ryzen 5 5600X 6-Core Processor
Cores1412
RAM64 GB47 GB
GPUApple M4 ProAD106 [GeForce RTX 4060 Ti]
OSmacOS 15.7.4cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5-9b-mlx qwen3.6-35b-a3b-cl…
Tokens/sec20.342.6
First chunk4216 ms13 ms
TTFT4.2 s3.1 s
Load timeN/AN/A
Memory usage5.6 GB23.2 GB
Memory %9%49%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
12/20
Memory
25/30

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

qwen3.6-35b-a3b-claude-…

Reasoning
20/20
Coding
16/20
Instruction
19/20
Structured
15/15
Math
14/15
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