ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
llama-3.2-1b-instruct
LM-STUDIO GGUFllama · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
71 vs 50
Hardware Fit
99 vs 79
Quality Score
59 vs 37
Hardware
ministral-3:3b llama-3.2-1b-instr…
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
ministral-3:3b llama-3.2-1b-instr…
Tokens/sec42.29.9
First chunk189 ms1668 ms
TTFT189 ms1.7 s
Load time1.2 sN/A
Memory usage7.0 GB0.8 GB
Memory %22%5%
HW Fit Score Breakdown
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
llama-3.2-1b-instruct
Speed
32/50
TTFT
20/20
Memory
27/30
Quality
ministral-3:3b
Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
llama-3.2-1b-instruct
Reasoning
4/20
Coding
3/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor 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