Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

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
53 vs 88
Hardware Fit
82 vs 85
Quality Score
41 vs 89

Hardware

qwen3.5:4b-mlx huihui-qwen3.6-35b…
MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M2AMD Ryzen 5 5600X 6-Core Processor
Cores812
RAM8 GB47 GB
GPUApple M2AD106 [GeForce RTX 4060 Ti]
OSmacOS 26.5.2cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5:4b-mlx huihui-qwen3.6-35b…
Tokens/sec24.737.7
First chunk302 ms18 ms
TTFT7.4 s2.9 s
Load time3.2 sN/A
Memory usage3.8 GB26.1 GB
Memory %47%56%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

huihui-qwen3.6-35b-a3b-…

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

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
View qwen3.5:4b-mlx details | View huihui-qwen3.6-35b… 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