qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
Global Score
78 vs 97
Hardware Fit
59 vs 95
Quality Score
86 vs 98
Hardware
qwen2.5-coder:32b qwen3-30b-a3b-thin…
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
qwen2.5-coder:32b qwen3-30b-a3b-thin…
Tokens/sec9.579.6
First chunk394 ms11 ms
TTFT395 ms1.7 s
Load time72.1 s7.1 s
Memory usage26.5 GB0.0 GB
Memory %22%0%
HW Fit Score Breakdown
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
qwen2.5-coder:32b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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