granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
starling-lm:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
66 vs 63
Hardware Fit
99 vs 97
Quality Score
52 vs 49
Hardware
granite3.1-moe:3b starling-lm:7b
MachineDell Inc. Inspiron 15 3530MacBook Air
CPUIntel Gen Intel® Core™ i7-1355UApple M4
Cores1210
RAM31 GB32 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
granite3.1-moe:3b starling-lm:7b
Tokens/sec27.223.7
First chunk527 msN/A
TTFT527 ms234 ms
Load time1.9 s0.4 s
Memory usage2.9 GB5.3 GB
Memory %9%17%
HW Fit Score Breakdown
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
starling-lm:7b
Speed
37/50
TTFT
30/20
Memory
30/30
Quality
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
starling-lm:7b
Reasoning
11/20
Coding
13/20
Instruction
6/20
Structured
3/15
Math
8/15
Multilingual
8/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Adequate 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