Back to leaderboard

deepseek-coder-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Excellent

Jun 26, 2026 · Cortex-X925

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

Global Score
82 vs 84
Hardware Fit
100 vs 97
Quality Score
74 vs 79

Hardware

deepseek-coder-v2:… qwen3:8b
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925Intel Core™ Ultra 9 285K
Cores2024
RAM122 GB47 GB
GPUDevice 2e12NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

deepseek-coder-v2:… qwen3:8b
Tokens/sec117.2208.0
First chunk275 ms82 ms
TTFT275 ms1.3 s
Load time8.9 s1.5 s
Memory usage17.9 GB9.6 GB
Memory %15%20%

HW Fit Score Breakdown

deepseek-coder-v2:16b

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

qwen3:8b

Speed
50/50
TTFT
18/20
Memory
29/30

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

qwen3:8b

Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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