deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Jun 26, 2026 · Cortex-X925
llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
Global Score
82 vs 81
Hardware Fit
100 vs 100
Quality Score
74 vs 73
Hardware
deepseek-coder-v2:… llama-3.1-8b-instr…
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925AMD Ryzen 5 5500
Cores2012
RAM122 GB31 GB
GPUDevice 2e12Navi 44 [Radeon RX 9060 XT]
OSUbuntu 24.04.4 LTSNobara Linux 43
Archarm64x64
Power Modeperformanceperformance
Performance
deepseek-coder-v2:… llama-3.1-8b-instr…
Tokens/sec117.235.6
First chunk275 ms52 ms
TTFT275 ms256 ms
Load time8.9 sN/A
Memory usage17.9 GB8.6 GB
Memory %15%28%
HW Fit Score Breakdown
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
Memory
30/30
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
deepseek-coder-v2:16b
Reasoning
8/20
Coding
19/20
Instruction
13/20
Structured
12/15
Math
14/15
Multilingual
8/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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