Back to leaderboard

smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
38 vs 18
Hardware Fit
98 vs 53
Quality Score
12 vs 3

Hardware

smollm2-135m-instr… qwen3.5:0.8b
MachineLENOVO 20BUS00700LENOVO 20L7CTO1WW
CPUIntel Core™ i5-5300UIntel Core™ i5-8350U
Cores48
RAM16 GB23 GB
GPUIntel(R) HD Graphics 5500Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 10 Professionnel 10.0.19045Fedora Linux 43
Archx64x64
Power Modebalancedlow-power

Performance

smollm2-135m-instr… qwen3.5:0.8b
Tokens/sec39.39.4
First chunk573 ms799 ms
TTFT573 ms30.0 s
Load timeN/A3.3 s
Memory usage0.1 GB1.9 GB
Memory %1%8%

HW Fit Score Breakdown

smollm2-135m-instruct

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

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
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

qwen3.5:0.8b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View smollm2-135m-instr… details | View qwen3.5:0.8b 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