smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
neural-chat:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
65 vs 67
Hardware Fit
99 vs 96
Quality Score
51 vs 55
Hardware
smollm2-1.7b-instr… neural-chat:7b
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… neural-chat:7b
Tokens/sec28.522.5
First chunk393 msN/A
TTFT393 ms242 ms
Load timeN/A0.4 s
Memory usage3.2 GB4.5 GB
Memory %10%14%
HW Fit Score Breakdown
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
neural-chat:7b
Speed
36/50
TTFT
30/20
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
neural-chat:7b
Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate 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