Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 752.39M · Q8_0

Not Rec.

Oct 11, 2026 · AMD Ryzen 5 5500

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
44 vs 82
Hardware Fit
80 vs 88
Quality Score
28 vs 80

Hardware

qwen3.5:0.8b 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

qwen3.5:0.8b unsloth-phi-4
Tokens/sec126.127.4
First chunk64 ms457 ms
TTFT30.0 s457 ms
Load time0.0 sN/A
Memory usage0.5 GB7.7 GB
Memory %7%12%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed
50/50
TTFT
0/20
Memory
30/30

unsloth-phi-4

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

Quality

qwen3.5:0.8b

Reasoning
9/20
Coding
0/20
Instruction
7/20
Structured
1/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate

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 qwen3.5:0.8b 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