Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

smollm2-360m-instruct

LM-STUDIO GGUF

llama · 360M · Q4_K_M

Marginal

Mar 5, 2026 · Intel Core™ i5-5300U

Global Score
18 vs 48
Hardware Fit
53 vs 98
Quality Score
3 vs 26

Hardware

qwen3.5:0.8b smollm2-360m-instr…
MachineLENOVO 20L7CTO1WWLENOVO 20BUS00700
CPUIntel Core™ i5-8350UIntel Core™ i5-5300U
Cores84
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Intel(R) HD Graphics 5500
OSFedora Linux 43Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:0.8b smollm2-360m-instr…
Tokens/sec9.420.0
First chunk799 ms1116 ms
TTFT30.0 s1.1 s
Load time3.3 sN/A
Memory usage1.9 GB0.3 GB
Memory %8%2%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
Memory
30/30

smollm2-360m-instruct

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

Quality

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

smollm2-360m-instruct

Reasoning
3/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
3/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Weak
View qwen3.5:0.8b details | View smollm2-360m-instr… 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