Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 1, 2026 · Intel Xeon® E5-2637 v3

Global Score
78 vs 80
Hardware Fit
59 vs 54
Quality Score
86 vs 91

Hardware

qwen2.5-coder:32b qwen3-next:80b-a3b…
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. Precision Tower 7910
CPUCortex-X925Intel Xeon® E5-2637 v3
Cores2016
RAM122 GB96 GB
GPUDevice 2e12NVIDIA GeForce RTX 5060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b qwen3-next:80b-a3b…
Tokens/sec9.514.9
First chunk394 ms1808 ms
TTFT395 ms1.8 s
Load time72.1 s95.0 s
Memory usage26.5 GB48.0 GB
Memory %22%50%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

qwen3-next:80b-a3b-inst…

Speed
16/50
TTFT
13/20
Memory
25/30

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-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest