Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

mlx-community/gemma-3-1b-it-8bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

Global Score
50 vs 72
Hardware Fit
93 vs 99
Quality Score
31 vs 61

Hardware

qwen3.5:4b mlx-community/gemm…
MachineMicrosoft WSLMacBook Air
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM8 GB32 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b mlx-community/gemm…
Tokens/sec92.686.3
First chunk323 ms253 ms
TTFT2.8 s253 ms
Load time9.0 sN/A
Memory usage2.9 GB1.1 GB
Memory %38%4%

HW Fit Score Breakdown

qwen3.5:4b

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

mlx-community/gemma-3-1…

Speed
50/50
TTFT
20/20
Memory
29/30

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

mlx-community/gemma-3-1…

Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.5:4b details | View mlx-community/gemm… 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