Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
61 vs 81
Hardware Fit
69 vs 100
Quality Score
58 vs 73

Hardware

qwen3.5:4b gemma3n:latest
MachineGigabyte Technology Co., Ltd. H170M-D3HSupermicro AS -2015HS-TNR
CPUIntel Core™ i5-6500AMD EPYC 9654P 96-Core Processor
Cores464
RAM16 GB128 GB
GPUGP104 [GeForce GTX 1070]GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSUbuntu 24.04.4 LTSUbuntu 24.04.3 LTS
Archx64x64
Power Modelow-powerperformance

Performance

qwen3.5:4b gemma3n:latest
Tokens/sec35.7108.7
First chunk438 ms333 ms
TTFT5.1 s333 ms
Load time40.1 s4.5 s
Memory usage5.5 GB8.6 GB
Memory %35%7%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

gemma3n:latest

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

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b details | View gemma3n:latest 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