Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

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

Global Score
77 vs 66
Hardware Fit
53 vs 99
Quality Score
87 vs 52

Hardware

qwen3.5:35b granite3.1-moe:3b
MachineASUSDell Inc. Inspiron 15 3530
CPUIntel Core™ i5-14600KFIntel Gen Intel® Core™ i7-1355U
Cores2012
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERRaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Famille 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3.5:35b granite3.1-moe:3b
Tokens/sec16.027.2
First chunk719 ms527 ms
TTFT719 ms527 ms
Load time17.8 s1.9 s
Memory usage25.0 GB2.9 GB
Memory %79%9%

HW Fit Score Breakdown

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

granite3.1-moe:3b

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

Quality

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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

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