qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
Global Score
84 vs 34
Hardware Fit
97 vs 100
Quality Score
79 vs 6
Hardware
qwen3:8b microllm-250m:latest
MachineASUSMac mini
CPUIntel Core™ Ultra 9 285KApple M4 Pro
Cores2412
RAM47 GB24 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b microllm-250m:latest
Tokens/sec208.0291.6
First chunk82 ms50 ms
TTFT1.3 s79 ms
Load time1.5 s0.0 s
Memory usage9.6 GB0.6 GB
Memory %20%2%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
microllm-250m:latest
Speed
50/50
TTFT
20/20
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
microllm-250m:latest
Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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