Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Good

Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H

Global Score
83 vs 76
Hardware Fit
100 vs 58
Quality Score
75 vs 84

Hardware

qwen3:8b qwen3:14b
MachineMicro-Star International Co., Ltd. Stealth GS77 12UHMicro-Star International Co., Ltd. Stealth GS77 12UH
CPUIntel Gen Intel® Core™ i9-12900HIntel Gen Intel® Core™ i9-12900H
Cores2020
RAM32 GB32 GB
GPUIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPUIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:8b qwen3:14b
Tokens/sec54.05.6
First chunk68 ms841 ms
TTFT68 ms841 ms
Load time6.1 s16.9 s
Memory usage5.8 GB10.1 GB
Memory %18%32%

HW Fit Score Breakdown

qwen3:8b

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

qwen3:14b

Speed
8/50
TTFT
20/20
Memory
30/30

Quality

qwen3:8b

Reasoning
15/20
Coding
15/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen3:14b

Reasoning
17/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:8b details | View qwen3:14b 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