qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
Global Score
68 vs 34
Hardware Fit
59 vs 100
Quality Score
72 vs 6
Hardware
qwen2.5-coder:7b microllm-250m:latest
MachineASUSMac mini
CPUIntel Gen Intel® Core™ i7-13700KApple M4 Pro
Cores2412
RAM64 GB24 GB
GPUNVIDIA GeForce RTX 3070Apple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.2
Archx64arm64
Power Modeunknownbalanced
Performance
qwen2.5-coder:7b microllm-250m:latest
Tokens/sec34.4291.6
First chunk1991 ms50 ms
TTFT2.0 s79 ms
Load time40.6 s0.0 s
Memory usage5.0 GB0.6 GB
Memory %8%2%
HW Fit Score Breakdown
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
microllm-250m:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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