Back to leaderboard

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

LM-STUDIO GGUF

mistral3 · 24B · IQ4_XS

Excellent

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

Ling-3.0-tiny-IQ4_XS:latest

OLLAMA GGUF

bailingmoe3 · 7.9B · IQ4_XS

Excellent

Aug 30, 2026 · Intel Core™ i7-7700HQ

Global Score
81 vs 87
Hardware Fit
80 vs 100
Quality Score
81 vs 82

Hardware

devstral-small-2-2… Ling-3.0-tiny-IQ4_…
MachineSystem manufacturerASUSTeK COMPUTER INC. GL702VMK
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ i7-7700HQ
Cores168
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce GTX 1060
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

devstral-small-2-2… Ling-3.0-tiny-IQ4_…
Tokens/sec21.524.7
First chunk12 ms283 ms
TTFT212 ms283 ms
Load timeN/A45.8 s
Memory usage15.9 GB4.3 GB
Memory %51%27%

HW Fit Score Breakdown

devstral-small-2-24b-in…

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

Ling-3.0-tiny-IQ4_XS:la…

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

Quality

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

Ling-3.0-tiny-IQ4_XS:la…

Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
9/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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