qwen3-coder-next:latest
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
82 vs 84
Hardware Fit
71 vs 82
Quality Score
87 vs 85
Hardware
qwen3-coder-next:l… gemma4:12b-mlx
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M2 Pro
Cores3210
RAM125 GB16 GB
GPUAMD Radeon 8060SApple M2 Pro
OSUbuntu 24.04.4 LTSmacOS 26.5
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3-coder-next:l… gemma4:12b-mlx
Tokens/sec34.527.2
First chunk262 ms732 ms
TTFT262 ms8.1 s
Load time16.4 s3.5 s
Memory usage56.8 GB7.1 GB
Memory %46%44%
HW Fit Score Breakdown
qwen3-coder-next:latest
Speed
34/50
TTFT
20/20
Memory
17/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
qwen3-coder-next:latest
Reasoning
18/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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