smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
gemma-3-270m-it-qat-mlx
LM-STUDIO MLXgemma3_text · 270M · 4bit
Mar 4, 2026 · Apple M4
Global Score
65 vs 43
Hardware Fit
99 vs 99
Quality Score
51 vs 19
Hardware
smollm2-1.7b-instr… gemma-3-270m-it-qa…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
smollm2-1.7b-instr… gemma-3-270m-it-qa…
Tokens/sec28.5344.2
First chunk393 ms173 ms
TTFT393 ms173 ms
Load timeN/AN/A
Memory usage3.2 GB0.3 GB
Memory %10%1%
HW Fit Score Breakdown
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
gemma-3-270m-it-qat-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
smollm2-1.7b-instruct
Reasoning
10/20
Coding
10/20
Instruction
13/20
Structured
11/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
gemma-3-270m-it-qat-mlx
Reasoning
4/20
Coding
0/20
Instruction
9/20
Structured
3/15
Math
1/15
Multilingual
2/10
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