Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

ornith-1.5:9b

OLLAMA GGUF

qwen35 · 9.0B · Q4_K_M

Good

Aug 24, 2026 · Apple M1 Pro

Global Score
65 vs 69
Hardware Fit
73 vs 95
Quality Score
62 vs 58

Hardware

qwen3.5:4b ornith-1.5:9b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPUAMD Radeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:4b ornith-1.5:9b
Tokens/sec45.722.2
First chunk180 ms341 ms
TTFT30.0 s341 ms
Load time5.3 s4.8 s
Memory usage16.2 GB7.1 GB
Memory %13%45%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

ornith-1.5:9b

Speed
49/50
TTFT
20/20
Memory
26/30

Quality

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong

ornith-1.5:9b

Reasoning
19/20
Coding
15/20
Instruction
6/20
Structured
2/15
Math
15/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View qwen3.5:4b details | View ornith-1.5:9b 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