smollm2-135m-instruct
LM-STUDIO GGUFllama · 135M · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 3, 2026 · Cortex-X925
Global Score
38 vs 84
Hardware Fit
98 vs 66
Quality Score
12 vs 92
Hardware
smollm2-135m-instr… qwen3.8:27b
MachineLENOVO 20BUS00700NVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-5300UCortex-X925
Cores420
RAM16 GB122 GB
GPUIntel(R) HD Graphics 5500Device 2e12
OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 24.04.5 LTS
Archx64arm64
Power Modebalancedperformance
Performance
smollm2-135m-instr… qwen3.8:27b
Tokens/sec39.329.4
First chunk573 ms306 ms
TTFT573 ms4.8 s
Load timeN/A5.3 s
Memory usage0.1 GB16.2 GB
Memory %1%13%
HW Fit Score Breakdown
smollm2-135m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3.8:27b
Speed
31/50
TTFT
5/20
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
qwen3.8:27b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest