devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
81 vs 63
Hardware Fit
80 vs 100
Quality Score
81 vs 47
Hardware
devstral-small-2-2… llama3.2:1b
MachineSystem manufacturerNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 7 5800X 8-Core ProcessorCortex-A78AE
Cores166
RAM31 GB7 GB
GPUNavi 44 [Radeon RX 9060 XT]Integrated / Unknown
OSUbuntu 26.04.1 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced
Performance
devstral-small-2-2… llama3.2:1b
Tokens/sec21.540.2
First chunk12 ms1087 ms
TTFT212 ms1.1 s
Load timeN/A6.2 s
Memory usage15.9 GB1.4 GB
Memory %51%19%
HW Fit Score Breakdown
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
llama3.2:1b
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
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest