Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
53 vs 63
Hardware Fit
82 vs 100
Quality Score
41 vs 47

Hardware

qwen3.5:4b-mlx llama3.2:1b
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M2Cortex-A78AE
Cores86
RAM8 GB7 GB
GPUApple M2Integrated / Unknown
OSmacOS 26.5.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx llama3.2:1b
Tokens/sec24.740.2
First chunk302 ms1087 ms
TTFT7.4 s1.1 s
Load time3.2 s6.2 s
Memory usage3.8 GB1.4 GB
Memory %47%19%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

llama3.2:1b

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

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

llama3.2:1b

Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3.5:4b-mlx details | View llama3.2:1b 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