smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score

38 vs 58

Hardware Fit

98 vs 82

Quality Score

12 vs 48

Hardware

smollm2-135m-instr… qwen3:14b

MachineLENOVO 20BUS00700MacBook Pro

CPUIntel Core™ i5-5300UApple M1 Max

Cores410

RAM16 GB32 GB

GPUIntel(R) HD Graphics 5500Apple M1 Max

OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

smollm2-135m-instr… qwen3:14b

Tokens/sec39.324.4

First chunk573 ms294 ms

TTFT573 ms7.9 s

Load timeN/A3.7 s

Memory usage0.1 GB13.8 GB

Memory %1%43%

HW Fit Score Breakdown

smollm2-135m-instruct

Speed

50/50

TTFT

20/20

Memory

28/30

qwen3:14b

Speed

47/50

TTFT

5/20

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

qwen3:14b

Reasoning

13/20

Coding

6/20

Instruction

10/20

Structured

9/15

Math

2/15

Multilingual

8/10

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

View smollm2-135m-instr… details | View qwen3:14b 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