llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
Feb 28, 2026 · Apple M4 Pro
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
Global Score
73 vs 61
Hardware Fit
100 vs 69
Quality Score
61 vs 58
Hardware
llama3.2:latest qwen3.5:4b
MachineMac MiniGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M4 ProIntel Core™ i5-6500
Cores144
RAM64 GB16 GB
GPUApple M4 ProGP104 [GeForce GTX 1070]
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64x64
Power Modeunknownlow-power
Performance
llama3.2:latest qwen3.5:4b
Tokens/sec98.935.7
First chunkN/A438 ms
TTFT125 ms5.1 s
Load time2.3 s40.1 s
Memory usage22.1 GB5.5 GB
Memory %35%35%
HW Fit Score Breakdown
llama3.2:latest
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
11/20
Memory
8/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
14/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
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
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