Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

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

Global Score
82 vs 66
Hardware Fit
93 vs 99
Quality Score
77 vs 52

Hardware

qwen3.5:4b granite3.1-moe:3b
MachineAZW GTR ProDell Inc. Inspiron 15 3530
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM125 GB31 GB
GPUIntegrated / Apple SiliconRaptor Lake-P [Iris Xe Graphics]
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

qwen3.5:4b granite3.1-moe:3b
Tokens/sec46.827.2
First chunk174 ms527 ms
TTFT174 ms527 ms
Load time5.9 s1.9 s
Memory usage16.2 GB2.9 GB
Memory %13%9%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
20/20
Memory
30/30

granite3.1-moe:3b

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

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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
View qwen3.5:4b details | View granite3.1-moe:3b 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