smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
65 vs 80
Hardware Fit
99 vs 100
Quality Score
51 vs 71
Hardware
smollm2-1.7b-instr… mlx-community/gemm…
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… mlx-community/gemm…
Tokens/sec28.543.2
First chunk393 ms428 ms
TTFT393 ms428 ms
Load timeN/AN/A
Memory usage3.2 GB1.3 GB
Memory %10%4%
HW Fit Score Breakdown
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
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
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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