smollm2-135m-instruct
LM-STUDIO GGUFllama · 135M · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
neural-chat:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
38 vs 67
Hardware Fit
98 vs 96
Quality Score
12 vs 55
Hardware
smollm2-135m-instr… neural-chat:7b
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… neural-chat:7b
Tokens/sec39.322.5
First chunk573 msN/A
TTFT573 ms242 ms
Load timeN/A0.4 s
Memory usage0.1 GB4.5 GB
Memory %1%14%
HW Fit Score Breakdown
smollm2-135m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
neural-chat:7b
Speed
36/50
TTFT
30/20
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
neural-chat:7b
Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak 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