Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

devstral-small-2-24b-instruct-2512

LM-STUDIO GGUF

mistral3 · 24B · IQ4_XS

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
90 vs 81
Hardware Fit
97 vs 80
Quality Score
87 vs 81

Hardware

qwen3:14b devstral-small-2-2…
MachineMacBook ProSystem manufacturer
CPUApple M1 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM32 GB31 GB
GPUApple M1 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3:14b devstral-small-2-2…
Tokens/sec24.021.5
First chunk300 ms12 ms
TTFT300 ms212 ms
Load time3.6 sN/A
Memory usage13.8 GB15.9 GB
Memory %43%51%

HW Fit Score Breakdown

qwen3:14b

Speed
47/50
TTFT
20/20
Memory
30/30

devstral-small-2-24b-in…

Speed
35/50
TTFT
20/20
Memory
25/30

Quality

qwen3:14b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

devstral-small-2-24b-in…

Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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