devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
81 vs 73
Hardware Fit
80 vs 51
Quality Score
81 vs 83
Hardware
devstral-small-2-2… llama3.3:70b
MachineSystem manufacturerNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 7 5800X 8-Core ProcessorCortex-X925
Cores1620
RAM31 GB122 GB
GPUNavi 44 [Radeon RX 9060 XT]Device 2e12
OSUbuntu 26.04.1 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance
Performance
devstral-small-2-2… llama3.3:70b
Tokens/sec21.54.6
First chunk12 ms560 ms
TTFT212 ms560 ms
Load timeN/A13.8 s
Memory usage15.9 GB49.5 GB
Memory %51%41%
HW Fit Score Breakdown
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
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
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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