Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
50 vs 66
Hardware Fit
93 vs 91
Quality Score
31 vs 55

Hardware

qwen3.5:4b qwen3.8-27b-mlx
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M5 Max
Cores1218
RAM8 GB64 GB
GPUIntegrated / UnknownApple M5 Max
OSUbuntu 26.04.1 LTSmacOS 27.0
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b qwen3.8-27b-mlx
Tokens/sec92.633.2
First chunk323 ms7 ms
TTFT2.8 s311 ms
Load time9.0 sN/A
Memory usage2.9 GB0.5 GB
Memory %38%1%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
15/20
Memory
28/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
12/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View qwen3.5:4b details | View qwen3.8-27b-mlx 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