Back to leaderboard

smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3-vl:2b

OLLAMA GGUF

qwen3vl · 2.1B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
38 vs 62
Hardware Fit
98 vs 99
Quality Score
12 vs 46

Hardware

smollm2-135m-instr… qwen3-vl:2b
MachineLENOVO 20BUS00700AZW GTR Pro
CPUIntel Core™ i5-5300UAMD RYZEN AI MAX+ 395
Cores432
RAM16 GB125 GB
GPUIntel(R) HD Graphics 5500AMD Radeon 8060S
OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

smollm2-135m-instr… qwen3-vl:2b
Tokens/sec39.3127.4
First chunk573 ms101 ms
TTFT573 ms630 ms
Load timeN/A5.9 s
Memory usage0.1 GB33.2 GB
Memory %1%27%

HW Fit Score Breakdown

smollm2-135m-instruct

Speed
50/50
TTFT
20/20
Memory
28/30

qwen3-vl:2b

Speed
50/50
TTFT
19/20
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-vl:2b

Reasoning
7/20
Coding
0/20
Instruction
11/20
Structured
7/15
Math
13/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
View smollm2-135m-instr… details | View qwen3-vl:2b 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