Back to leaderboard

smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Qwen3-Coder-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score
38 vs 91
Hardware Fit
98 vs 100
Quality Score
12 vs 87

Hardware

smollm2-135m-instr… Qwen3-Coder-30B:30b
MachineLENOVO 20BUS00700HP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUIntel Core™ i5-5300UIntel Core™ i7-14700F
Cores428
RAM16 GB128 GB
GPUIntel(R) HD Graphics 5500NVIDIA GeForce RTX 5080
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

smollm2-135m-instr… Qwen3-Coder-30B:30b
Tokens/sec39.374.0
First chunk573 ms381 ms
TTFT573 ms381 ms
Load timeN/A15.3 s
Memory usage0.1 GB17.9 GB
Memory %1%14%

HW Fit Score Breakdown

smollm2-135m-instruct

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

Qwen3-Coder-30B:30b

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

Qwen3-Coder-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View smollm2-135m-instr… details | View Qwen3-Coder-30B:30b 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