Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

huihui-devstral-small-2-24b-instruct-2512-abliterated-i1

LM-STUDIO GGUF

mistral3 · 24B · Q4_K_S

Good

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
90 vs 78
Hardware Fit
97 vs 74
Quality Score
87 vs 79

Hardware

qwen3:14b huihui-devstral-sm…
MachineMacBook ProSystem manufacturer
CPUApple M1 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM32 GB32 GB
GPUApple M1 MaxAMD Radeon RX 9060 XT
OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3:14b huihui-devstral-sm…
Tokens/sec24.017.5
First chunk300 ms20 ms
TTFT300 ms279 ms
Load time3.6 sN/A
Memory usage13.8 GB15.6 GB
Memory %43%49%

HW Fit Score Breakdown

qwen3:14b

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

huihui-devstral-small-2…

Speed
29/50
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

huihui-devstral-small-2…

Reasoning
16/20
Coding
17/20
Instruction
15/20
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