smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
65 vs 76
Hardware Fit
99 vs 82
Quality Score
51 vs 73
Hardware
smollm2-1.7b-instr… gemma4:e2b
MachineMacBook AirLENOVO 20U30029MB
CPUApple M4Intel Core™ i5-10210U
Cores108
RAM32 GB15 GB
GPUApple M4CometLake-U GT2 [UHD Graphics]
OSmacOS 26.3Pop 24.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
smollm2-1.7b-instr… gemma4:e2b
Tokens/sec28.513.5
First chunk393 ms1270 ms
TTFT393 ms1.3 s
Load timeN/A13.4 s
Memory usage3.2 GB6.5 GB
Memory %10%42%
HW Fit Score Breakdown
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
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
gemma4:e2b
Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate 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