granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
66 vs 69
Hardware Fit
99 vs 85
Quality Score
52 vs 62
Hardware
granite3.1-moe:3b qwen3.5:4b
MachineDell Inc. Inspiron 15 3530MacBook Pro
CPUIntel Gen Intel® Core™ i7-1355UApple M1 Pro
Cores1210
RAM31 GB16 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M1 Pro
OScachyos rollingmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
granite3.1-moe:3b qwen3.5:4b
Tokens/sec27.236.9
First chunk527 ms474 ms
TTFT527 ms6.9 s
Load time1.9 s2.9 s
Memory usage2.9 GB5.3 GB
Memory %9%33%
HW Fit Score Breakdown
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
6/20
Memory
29/30
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
qwen3.5:4b
Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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