Back to leaderboard

deepseek-coder-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Excellent

Jun 26, 2026 · Cortex-X925

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
82 vs 78
Hardware Fit
100 vs 47
Quality Score
74 vs 92

Hardware

deepseek-coder-v2:… gemma4:31b
MachineNVIDIA NVIDIA_DGX_SparkAZW GTR Pro
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB125 GB
GPUDevice 2e12Radeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modeperformanceperformance

Performance

deepseek-coder-v2:… gemma4:31b
Tokens/sec117.29.8
First chunk275 ms873 ms
TTFT275 ms873 ms
Load time8.9 s7.0 s
Memory usage17.9 GB68.3 GB
Memory %15%55%

HW Fit Score Breakdown

deepseek-coder-v2:16b

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

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

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

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View deepseek-coder-v2:… details | View gemma4:31b details

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