smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score

38 vs 64

Hardware Fit

98 vs 69

Quality Score

12 vs 62

Hardware

smollm2-135m-instr… qwen3.5:4b

MachineLENOVO 20BUS00700LENOVO 20U30029MB

CPUIntel Core™ i5-5300UIntel Core™ i5-10210U

Cores48

RAM16 GB15 GB

GPUIntel(R) HD Graphics 5500CometLake-U GT2 [UHD Graphics]

OSMicrosoft Windows 10 Professionnel 10.0.19045Pop 24.04 LTS

Archx64x64

Power Modebalancedperformance

Performance

smollm2-135m-instr… qwen3.5:4b

Tokens/sec39.37.4

First chunk573 ms1815 ms

TTFT573 ms1.8 s

Load timeN/A10.9 s

Memory usage0.1 GB3.5 GB

Memory %1%23%

HW Fit Score Breakdown

smollm2-135m-instruct

Speed

50/50

TTFT

20/20

Memory

28/30

qwen3.5:4b

Speed

19/50

TTFT

20/20

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

qwen3.5:4b

Reasoning

15/20

Coding

14/20

Instruction

6/20

Structured

12/15

Math

6/15

Multilingual

9/10

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

View smollm2-135m-instr… details | View qwen3.5:4b 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