Back to leaderboard

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

Global Score
73 vs 88
Hardware Fit
100 vs 90
Quality Score
62 vs 87

Hardware

mistral:latest Qwen3-30B:30b
MachineMicro-Star International Co., Ltd. MS-7B79GMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Core™ Ultra X7 358H
Cores1216
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Intel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

mistral:latest Qwen3-30B:30b
Tokens/sec31.731.3
First chunk102 ms560 ms
TTFT102 ms560 ms
Load time14.3 s15.4 s
Memory usage4.8 GB17.7 GB
Memory %30%28%

HW Fit Score Breakdown

mistral:latest

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

Qwen3-30B:30b

Speed
40/50
TTFT
20/20
Memory
30/30

Quality

mistral:latest

Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

Qwen3-30B:30b

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: Strong Multilingual: Strong
View mistral:latest details | View Qwen3-30B:30b 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