Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

Qwen3.6-35B-A3B-Q4_K_M:latest

OLLAMA GGUF

qwen35moe · 34.7B · Q4_K_M

Excellent

Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
59 vs 86
Hardware Fit
65 vs 87
Quality Score
57 vs 86

Hardware

qwen3.5-9b-mlx Qwen3.6-35B-A3B-Q4…
MachineMac miniMicro-Star International Co., Ltd. MS-7E51
CPUApple M4AMD Ryzen 7 9700X 8-Core Processor
Cores1016
RAM24 GB31 GB
GPUApple M4NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx Qwen3.6-35B-A3B-Q4…
Tokens/sec14.392.9
First chunk24 ms362 ms
TTFT13.4 s362 ms
Load time13.3 s12.3 s
Memory usage2.5 GB20.7 GB
Memory %10%67%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

Qwen3.6-35B-A3B-Q4_K_M:…

Speed
50/50
TTFT
20/20
Memory
17/30

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

Qwen3.6-35B-A3B-Q4_K_M:…

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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