smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

phi3:3.8b

OLLAMA GGUF

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

38 vs 64

Hardware Fit

98 vs 100

Quality Score

12 vs 48

Hardware

smollm2-135m-instr… phi3:3.8b

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

smollm2-135m-instr… phi3:3.8b

Tokens/sec39.342.0

First chunk573 msN/A

TTFT573 ms142 ms

Load timeN/A1.1 s

Memory usage0.1 GB16.0 GB

Memory %1%50%

HW Fit Score Breakdown

smollm2-135m-instruct

Speed

50/50

TTFT

20/20

Memory

28/30

phi3:3.8b

Speed

40/50

TTFT

30/20

Memory

30/30

Quality

smollm2-135m-instruct

Reasoning

2/20

Coding

1/20

Instruction

5/20

Structured

3/15

Math

0/15

Multilingual

1/10

Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

phi3:3.8b

Reasoning

12/20

Coding

3/20

Instruction

11/20

Structured

10/15

Math

5/15

Multilingual

7/10

Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate

View smollm2-135m-instr… details | View phi3:3.8b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest