llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
73 vs 81
Hardware Fit
51 vs 80
Quality Score
83 vs 81
Hardware
llama3.3:70b devstral-small-2-2…
MachineNVIDIA NVIDIA_DGX_SparkSystem manufacturer
CPUCortex-X925AMD Ryzen 7 5800X 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12Navi 44 [Radeon RX 9060 XT]
OSUbuntu 24.04.4 LTSUbuntu 26.04.1 LTS
Archarm64x64
Power Modeperformanceperformance
Performance
llama3.3:70b devstral-small-2-2…
Tokens/sec4.621.5
First chunk560 ms12 ms
TTFT560 ms212 ms
Load time13.8 sN/A
Memory usage49.5 GB15.9 GB
Memory %41%51%
HW Fit Score Breakdown
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
Quality
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
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest