Back to leaderboard

Qwen3-Next-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · unknown

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

qwen2.5-coder:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
25 vs 73
Hardware Fit
71 vs 100
Quality Score
5 vs 61

Hardware

Qwen3-Next-80B:80B qwen2.5-coder:3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i7-14700FCortex-A78AE
Cores286
RAM128 GB7 GB
GPUNVIDIA GeForce RTX 5080Integrated / Unknown
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-Next-80B:80B qwen2.5-coder:3b
Tokens/sec29.121.3
First chunk815 ms969 ms
TTFT769 ms969 ms
Load time56.9 s6.6 s
Memory usage61.7 GB2.0 GB
Memory %48%27%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

Speed
29/50
TTFT
17/20
Memory
25/30

qwen2.5-coder:3b

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

Quality

Qwen3-Next-80B:80B

Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

qwen2.5-coder:3b

Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View Qwen3-Next-80B:80B details | View qwen2.5-coder:3b 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