qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Feb 28, 2026 · Apple M4
Global Score
61 vs 68
Hardware Fit
69 vs 98
Quality Score
58 vs 55
Hardware
qwen3.5:4b gemma3:1b
MachineGigabyte Technology Co., Ltd. H170M-D3HMacBook Air
CPUIntel Core™ i5-6500Apple M4
Cores410
RAM16 GB32 GB
GPUGP104 [GeForce GTX 1070]Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerunknown
Performance
qwen3.5:4b gemma3:1b
Tokens/sec35.739.5
First chunk438 msN/A
TTFT5.1 s333 ms
Load time40.1 s1.6 s
Memory usage5.5 GB1.3 GB
Memory %35%4%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
11/20
Memory
8/30
gemma3:1b
Speed
40/50
TTFT
30/20
Memory
28/30
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
gemma3:1b
Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest