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-coder:30b-a3b-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

Global Score
70 vs 91
Hardware Fit
73 vs 100
Quality Score
68 vs 87

Hardware

llama3.1:8b-instru… qwen3-coder:30b-a3…
Machine—Micro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUC1-ProIntel Core™ Ultra 9 285HX
Cores024
RAM11 GB63 GB
GPUIntegrated / UnknownIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSunknown unknownMicrosoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… qwen3-coder:30b-a3…
Tokens/sec6.5175.3
First chunk950 ms224 ms
TTFT950 ms224 ms
Load time11.5 s6.1 s
Memory usage4.4 GB18.7 GB
Memory %38%30%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

qwen3-coder:30b-a3b-q4_…

Speed
50/50
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-coder:30b-a3b-q4_…

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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