Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
53 vs 83
Hardware Fit
81 vs 68
Quality Score
41 vs 90

Hardware

qwen3.5:4b-mlx qwen/qwen3.8-27b
MachineMac miniMacBook Pro
CPUApple M2Apple M4 Max
Cores816
RAM8 GB128 GB
GPUApple M2Apple M4 Max
OSmacOS 26.5.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx qwen/qwen3.8-27b
Tokens/sec24.827.6
First chunk317 ms10 ms
TTFT7.4 s4.6 s
Load time0.0 sN/A
Memory usage3.9 GB21.0 GB
Memory %49%16%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

qwen/qwen3.8-27b

Speed
32/50
TTFT
6/20
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

qwen/qwen3.8-27b

Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b-mlx details | View qwen/qwen3.8-27b 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