qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
78 vs 76
Hardware Fit
59 vs 51
Quality Score
86 vs 87
Hardware
qwen2.5-coder:32b qwen3-coder:latest
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. Inspiron 15 3530
CPUCortex-X925Intel Gen Intel® Core™ i7-1355U
Cores2012
RAM122 GB31 GB
GPUDevice 2e12Raptor Lake-P [Iris Xe Graphics]
OSUbuntu 24.04.4 LTScachyos rolling
Archarm64x64
Power Modeperformancelow-power
Performance
qwen2.5-coder:32b qwen3-coder:latest
Tokens/sec9.57.6
First chunk394 ms2037 ms
TTFT395 ms2.0 s
Load time72.1 s8.7 s
Memory usage26.5 GB18.9 GB
Memory %22%61%
HW Fit Score Breakdown
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
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-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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