gemma-3-1b-it
LM-STUDIO GGUFgemma3 · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
qwen2.5-math-1.5b-instruct
LM-STUDIO MLXqwen2 · 1.5B · 4bit
Mar 4, 2026 · Apple M4
Global Score
59 vs 45
Hardware Fit
76 vs 99
Quality Score
52 vs 22
Hardware
gemma-3-1b-it qwen2.5-math-1.5b-…
MachineLENOVO 20BUS00700MacBook Air
CPUIntel Core™ i5-5300UApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500Apple M4
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
gemma-3-1b-it qwen2.5-math-1.5b-…
Tokens/sec8.791.7
First chunk2078 ms205 ms
TTFT2.1 s205 ms
Load timeN/AN/A
Memory usage0.8 GB0.8 GB
Memory %5%3%
HW Fit Score Breakdown
gemma-3-1b-it
Speed
29/50
TTFT
19/20
Memory
28/30
qwen2.5-math-1.5b-instr…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
gemma-3-1b-it
Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
qwen2.5-math-1.5b-instr…
Reasoning
2/20
Coding
0/20
Instruction
3/20
Structured
1/15
Math
14/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong 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