qwen2.5-1.5b-instruct
LM-STUDIO GGUFqwen2 · 1.5B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
61 vs 91
Hardware Fit
69 vs 96
Quality Score
58 vs 89
Hardware
qwen2.5-1.5b-instr… gemma4:12b-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M2 Pro
Cores410
RAM16 GB16 GB
GPUIntel(R) HD Graphics 5500Apple M2 Pro
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5-1.5b-instr… gemma4:12b-mlx
Tokens/sec6.624.7
First chunk2277 ms610 ms
TTFT2.3 s610 ms
Load timeN/A3.6 s
Memory usage0.9 GB7.1 GB
Memory %6%45%
HW Fit Score Breakdown
qwen2.5-1.5b-instruct
Speed
23/50
TTFT
19/20
Memory
27/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
qwen2.5-1.5b-instruct
Reasoning
9/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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