Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Good

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

Global Score
70 vs 76
Hardware Fit
73 vs 58
Quality Score
68 vs 84

Hardware

llama3.1:8b-instru… qwen3:14b
Machine—Micro-Star International Co., Ltd. Stealth GS77 12UH
CPUC1-ProIntel Gen Intel® Core™ i9-12900H
Cores020
RAM11 GB32 GB
GPUIntegrated / UnknownIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPU
OSunknown unknownMicrosoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… qwen3:14b
Tokens/sec6.55.6
First chunk950 ms841 ms
TTFT950 ms841 ms
Load time11.5 s16.9 s
Memory usage4.4 GB10.1 GB
Memory %38%32%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

qwen3:14b

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

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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

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