Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
81 vs 82
Hardware Fit
98 vs 88
Quality Score
74 vs 80

Hardware

qwen3.5:4b unsloth-phi-4
MachineMicrosoft WSLMac mini
CPUAMD Ryzen 5 5500Apple M4 Pro
Cores1214
RAM8 GB64 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 26.04.1 LTSmacOS 15.7.4
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b unsloth-phi-4
Tokens/sec93.727.4
First chunk249 ms457 ms
TTFT249 ms457 ms
Load time10.1 sN/A
Memory usage2.9 GB7.7 GB
Memory %38%12%

HW Fit Score Breakdown

qwen3.5:4b

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

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View unsloth-phi-4 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