llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
qwen3-vl:4b-instruct
OLLAMA GGUFqwen3vl · 4.4B · Q4_K_M
Apr 20, 2026 · Apple M2 Max
Global Score
76 vs 83
Hardware Fit
100 vs 96
Quality Score
65 vs 78
Hardware
llama3.2:latest qwen3-vl:4b-instruct
MachineMicro-Star International Co., Ltd. MS-7B79Mac Studio
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M2 Max
Cores1212
RAM16 GB96 GB
GPUNVIDIA GeForce GTX 1080Apple M2 Max
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.2:latest qwen3-vl:4b-instruct
Tokens/sec57.090.6
First chunk264 ms159 ms
TTFT264 ms159 ms
Load time9.7 s5.8 s
Memory usage2.6 GB42.5 GB
Memory %16%44%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-vl:4b-instruct
Speed
50/50
TTFT
20/20
Memory
26/30
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-vl:4b-instruct
Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong 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