Back to leaderboard

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
87 vs 78
Hardware Fit
76 vs 59
Quality Score
91 vs 86

Hardware

Qwen3-80B:80B qwen2.5-coder:32b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLNVIDIA NVIDIA_DGX_Spark
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Cortex-X925
Cores2020
RAM55 GB122 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.28000Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

Qwen3-80B:80B qwen2.5-coder:32b
Tokens/sec43.69.5
First chunk409 ms394 ms
TTFT409 ms395 ms
Load time80.3 s72.1 s
Memory usage48.0 GB26.5 GB
Memory %88%22%

HW Fit Score Breakdown

Qwen3-80B:80B

Speed
50/50
TTFT
20/20
Memory
6/30

qwen2.5-coder:32b

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

Quality

Qwen3-80B:80B

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

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
View Qwen3-80B:80B details | View qwen2.5-coder:32b details

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