Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen3-0.6b

LM-STUDIO GGUF

qwen3 · 0.6B · Q4_K_M

Marginal

Mar 5, 2026 · Intel Core™ i5-5300U

Global Score
78 vs 40
Hardware Fit
59 vs 89
Quality Score
86 vs 19

Hardware

qwen2.5-coder:32b qwen3-0.6b
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20BUS00700
CPUCortex-X925Intel Core™ i5-5300U
Cores204
RAM122 GB16 GB
GPUDevice 2e12Intel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b qwen3-0.6b
Tokens/sec9.514.4
First chunk394 ms854 ms
TTFT395 ms854 ms
Load time72.1 sN/A
Memory usage26.5 GB0.5 GB
Memory %22%3%

HW Fit Score Breakdown

qwen2.5-coder:32b

Speed
9/50
TTFT
20/20
Memory
30/30

qwen3-0.6b

Speed
43/50
TTFT
20/20
Memory
26/30

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

qwen3-0.6b

Reasoning
5/20
Coding
1/20
Instruction
3/20
Structured
4/15
Math
0/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Poor Multilingual: Adequate

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