Back to leaderboard

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

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

Global Score
62 vs 66
Hardware Fit
10 vs 99
Quality Score
84 vs 52

Hardware

Qwen3-80B:80B granite3.1-moe:3b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxDell Inc. Inspiron 15 3530
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM31 GB31 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPURaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Home 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

Qwen3-80B:80B granite3.1-moe:3b
Tokens/sec4.927.2
First chunk8006 ms527 ms
TTFT8.0 s527 ms
Load time63.7 s1.9 s
Memory usage47.3 GB2.9 GB
Memory %153%9%

HW Fit Score Breakdown

Qwen3-80B:80B

Speed
6/50
TTFT
4/20
Memory
0/30

granite3.1-moe:3b

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

Quality

Qwen3-80B:80B

Reasoning
17/20
Coding
19/20
Instruction
13/20
Structured
13/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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
View Qwen3-80B:80B 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