Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen2.5-1.5b-instruct

LM-STUDIO GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
53 vs 61
Hardware Fit
82 vs 69
Quality Score
41 vs 58

Hardware

qwen3.5:4b-mlx qwen2.5-1.5b-instr…
MachineMac miniLENOVO 20BUS00700
CPUApple M2Intel Core™ i5-5300U
Cores84
RAM8 GB16 GB
GPUApple M2Intel(R) HD Graphics 5500
OSmacOS 26.5.2Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx qwen2.5-1.5b-instr…
Tokens/sec24.76.6
First chunk302 ms2277 ms
TTFT7.4 s2.3 s
Load time3.2 sN/A
Memory usage3.8 GB0.9 GB
Memory %47%6%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

qwen2.5-1.5b-instruct

Speed
23/50
TTFT
19/20
Memory
27/30

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

qwen2.5-1.5b-instruct

Reasoning
9/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b-mlx details | View qwen2.5-1.5b-instr… 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