granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
66 vs 59
Hardware Fit
99 vs 63
Quality Score
52 vs 58
Hardware
granite3.1-moe:3b qwen3.8-27b-mlx
MachineDell Inc. Inspiron 15 3530MacBook Pro
CPUIntel Gen Intel® Core™ i7-1355UApple M5 Max
Cores1218
RAM31 GB64 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M5 Max
OScachyos rollingmacOS 27.0
Archx64arm64
Power Modelow-powerbalanced
Performance
granite3.1-moe:3b qwen3.8-27b-mlx
Tokens/sec27.218.3
First chunk527 ms4 ms
TTFT527 ms530 ms
Load time1.9 sN/A
Memory usage2.9 GB38.5 GB
Memory %9%60%
HW Fit Score Breakdown
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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