qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
76 vs 78
Hardware Fit
51 vs 59
Quality Score
87 vs 86
Hardware
qwen3-coder:latest qwen2.5-coder:32b
MachineDell Inc. Inspiron 15 3530NVIDIA NVIDIA_DGX_Spark
CPUIntel Gen Intel® Core™ i7-1355UCortex-X925
Cores1220
RAM31 GB122 GB
GPURaptor Lake-P [Iris Xe Graphics]Device 2e12
OScachyos rollingUbuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance
Performance
qwen3-coder:latest qwen2.5-coder:32b
Tokens/sec7.69.5
First chunk2037 ms394 ms
TTFT2.0 s395 ms
Load time8.7 s72.1 s
Memory usage18.9 GB26.5 GB
Memory %61%22%
HW Fit Score Breakdown
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
Quality
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
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
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