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

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Core™ i9-14900K

Global Score
66 vs 83
Hardware Fit
99 vs 70
Quality Score
52 vs 89

Hardware

granite3.1-moe:3b qwen3:30b-a3b-inst…
MachineDell Inc. Inspiron 15 3530Micro-Star International Co., Ltd. MS-7D98
CPUIntel Gen Intel® Core™ i7-1355UIntel Core™ i9-14900K
Cores1232
RAM31 GB128 GB
GPURaptor Lake-P [Iris Xe Graphics]Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

granite3.1-moe:3b qwen3:30b-a3b-inst…
Tokens/sec27.221.2
First chunk527 ms468 ms
TTFT527 ms468 ms
Load time1.9 s9.6 s
Memory usage2.9 GB17.7 GB
Memory %9%14%

HW Fit Score Breakdown

granite3.1-moe:3b

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

qwen3:30b-a3b-instruct-…

Speed
20/50
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

qwen3:30b-a3b-instruct-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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