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-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Good

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score

66 vs 78

Hardware Fit

99 vs 56

Quality Score

52 vs 87

Hardware

granite3.1-moe:3b qwen3.8-27b-uncens…

MachineDell Inc. Inspiron 15 3530System manufacturer

CPUIntel Gen Intel® Core™ i7-1355UAMD Ryzen 7 5800X 8-Core Processor

Cores1216

RAM31 GB31 GB

GPURaptor Lake-P [Iris Xe Graphics]Navi 44 [Radeon RX 9060 XT]

OScachyos rollingUbuntu 26.04.1 LTS

Archx64x64

Power Modelow-powerperformance

Performance

granite3.1-moe:3b qwen3.8-27b-uncens…

Tokens/sec27.27.0

First chunk527 ms19 ms

TTFT527 ms1.2 s

Load time1.9 sN/A

Memory usage2.9 GB15.6 GB

Memory %9%50%

HW Fit Score Breakdown

granite3.1-moe:3b

Speed

49/50

TTFT

20/20

Memory

30/30

qwen3.8-27b-uncensored-…

Speed

11/50

TTFT

20/20

Memory

25/30

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-uncensored-…

Reasoning

17/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

11/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

View granite3.1-moe:3b details | View qwen3.8-27b-uncens… details

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