Back to leaderboard

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
66 vs 66
Hardware Fit
99 vs 91
Quality Score
52 vs 55

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/sec27.233.2
First chunk527 ms7 ms
TTFT527 ms311 ms
Load time1.9 sN/A
Memory usage2.9 GB0.5 GB
Memory %9%1%

HW Fit Score Breakdown

granite3.1-moe:3b

Speed
49/50
TTFT
20/20
Memory
30/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest