qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
qwen2.5:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
84 vs 57
Hardware Fit
97 vs 100
Quality Score
79 vs 39
Hardware
qwen3:8b qwen2.5:0.5b
MachineASUSMacBook Air
CPUIntel Core™ Ultra 9 285KApple M4
Cores2410
RAM47 GB32 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b qwen2.5:0.5b
Tokens/sec208.0165.0
First chunk82 msN/A
TTFT1.3 s81 ms
Load time1.5 s0.5 s
Memory usage9.6 GB1.7 GB
Memory %20%5%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
qwen2.5:0.5b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5:0.5b
Reasoning
6/20
Coding
6/20
Instruction
7/20
Structured
11/15
Math
5/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Weak Multilingual: Weak
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