Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

gemma4:26b-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
50 vs 85
Hardware Fit
93 vs 80
Quality Score
31 vs 87

Hardware

qwen3.5:4b gemma4:26b-nvfp4
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M4 Pro
Cores1214
RAM8 GB48 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 26.04.1 LTSmacOS 26.4.1
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b gemma4:26b-nvfp4
Tokens/sec92.665.7
First chunk323 ms233 ms
TTFT2.8 s30.0 s
Load time9.0 s5.0 s
Memory usage2.9 GB15.2 GB
Memory %38%32%

HW Fit Score Breakdown

qwen3.5:4b

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

gemma4:26b-nvfp4

Speed
50/50
TTFT
0/20
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

gemma4:26b-nvfp4

Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View gemma4:26b-nvfp4 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