Back to leaderboard

deepseek-coder-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Excellent

Jun 26, 2026 · Cortex-X925

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
82 vs 83
Hardware Fit
100 vs 96
Quality Score
74 vs 78

Hardware

deepseek-coder-v2:… qwen3-vl:4b-instruct
MachineNVIDIA NVIDIA_DGX_SparkMac Studio
CPUCortex-X925Apple M2 Max
Cores2012
RAM122 GB96 GB
GPUDevice 2e12Apple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archarm64arm64
Power Modeperformancebalanced

Performance

deepseek-coder-v2:… qwen3-vl:4b-instruct
Tokens/sec117.291.2
First chunk275 ms150 ms
TTFT275 ms150 ms
Load time8.9 s5.3 s
Memory usage17.9 GB42.5 GB
Memory %15%44%

HW Fit Score Breakdown

deepseek-coder-v2:16b

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

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

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-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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