Back to leaderboard

smollm2-1.7b-instruct

LM-STUDIO GGUF

llama · 1.7B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

gemma-4-26b-a4b-it@iq3_xxs

LM-STUDIO GGUF

gemma4 · 26B · IQ3_XXS

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
48 vs 83
Hardware Fit
63 vs 58
Quality Score
41 vs 94

Hardware

smollm2-1.7b-instr… gemma-4-26b-a4b-it…
MachineLENOVO 20BUS00700Docker Container
CPUIntel Core™ i5-5300UIntel Gen Intel® Core™ i9-11900H
Cores416
RAM16 GB15 GB
GPUIntel(R) HD Graphics 5500TigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

smollm2-1.7b-instr… gemma-4-26b-a4b-it…
Tokens/sec6.610.3
First chunk3184 ms8 ms
TTFT3.2 s3.5 s
Load timeN/A10.9 s
Memory usage1.0 GB6.4 GB
Memory %6%41%

HW Fit Score Breakdown

smollm2-1.7b-instruct

Speed
23/50
TTFT
15/20
Memory
25/30

gemma-4-26b-a4b-it@iq3_…

Speed
19/50
TTFT
12/20
Memory
27/30

Quality

smollm2-1.7b-instruct

Reasoning
5/20
Coding
7/20
Instruction
12/20
Structured
10/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

gemma-4-26b-a4b-it@iq3_…

Reasoning
18/20
Coding
19/20
Instruction
19/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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