Back to leaderboard

smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
38 vs 81
Hardware Fit
98 vs 100
Quality Score
12 vs 73

Hardware

smollm2-135m-instr… llama-3.1-8b-instr…
MachineLENOVO 20BUS00700ASUS
CPUIntel Core™ i5-5300UAMD Ryzen 5 5500
Cores412
RAM16 GB31 GB
GPUIntel(R) HD Graphics 5500Navi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 10 Professionnel 10.0.19045Nobara Linux 43
Archx64x64
Power Modebalancedperformance

Performance

smollm2-135m-instr… llama-3.1-8b-instr…
Tokens/sec39.335.6
First chunk573 ms52 ms
TTFT573 ms256 ms
Load timeN/AN/A
Memory usage0.1 GB8.6 GB
Memory %1%28%

HW Fit Score Breakdown

smollm2-135m-instruct

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

llama-3.1-8b-instruct

Speed
50/50
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

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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