Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

Global Score
65 vs 71
Hardware Fit
73 vs 35
Quality Score
62 vs 86

Hardware

qwen3.5:4b google/gemma-3-27b
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB24 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:4b google/gemma-3-27b
Tokens/sec45.75.9
First chunk180 ms19 ms
TTFT30.0 s1.8 s
Load time5.3 sN/A
Memory usage16.2 GB22.0 GB
Memory %13%92%

HW Fit Score Breakdown

qwen3.5:4b

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

google/gemma-3-27b

Speed
12/50
TTFT
19/20
Memory
4/30

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

google/gemma-3-27b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View google/gemma-3-27b 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