llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
Global Score
76 vs 48
Hardware Fit
100 vs 77
Quality Score
65 vs 35
Hardware
llama3.2:latest qwen3.5:4b
MachineMicro-Star International Co., Ltd. MS-7B79Mac mini
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M4
Cores1210
RAM16 GB16 GB
GPUNVIDIA GeForce GTX 1080Apple M4
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.2:latest qwen3.5:4b
Tokens/sec57.018.9
First chunk264 ms316 ms
TTFT264 ms13.0 s
Load time9.7 s3.7 s
Memory usage2.6 GB5.9 GB
Memory %16%37%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:4b
Speed
43/50
TTFT
4/20
Memory
30/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
qwen3.5:4b
Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate 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