smollm2-135m-instruct
LM-STUDIO GGUFllama · 135M · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
dolphin3:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
38 vs 74
Hardware Fit
98 vs 92
Quality Score
12 vs 66
Hardware
smollm2-135m-instr… dolphin3:8b
MachineLENOVO 20BUS00700MacBook Air
CPUIntel Core™ i5-5300UApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500Apple M4
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
smollm2-135m-instr… dolphin3:8b
Tokens/sec39.321.0
First chunk573 ms314 ms
TTFT573 ms314 ms
Load timeN/A0.8 s
Memory usage0.1 GB10.4 GB
Memory %1%33%
HW Fit Score Breakdown
smollm2-135m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
dolphin3:8b
Speed
42/50
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
dolphin3:8b
Reasoning
12/20
Coding
13/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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