Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Qwen3.8-27B-Opus-Distill-IQ3_XXS:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ3_XXS

Excellent

Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
78 vs 90
Hardware Fit
59 vs 98
Quality Score
86 vs 86

Hardware

qwen2.5-coder:32b Qwen3.8-27B-Opus-D…
MachineNVIDIA NVIDIA_DGX_SparkMicro-Star International Co., Ltd. MS-7E51
CPUCortex-X925AMD Ryzen 7 9700X 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b Qwen3.8-27B-Opus-D…
Tokens/sec9.561.8
First chunk394 ms325 ms
TTFT395 ms325 ms
Load time72.1 s5.5 s
Memory usage26.5 GB12.2 GB
Memory %22%39%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

Qwen3.8-27B-Opus-Distil…

Speed
50/50
TTFT
20/20
Memory
28/30

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

Qwen3.8-27B-Opus-Distil…

Reasoning
16/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
12/15
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