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:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
25 vs 78
Hardware Fit
71 vs 59
Quality Score
5 vs 86

Hardware

Qwen3-Next-80B:80B qwen2.5-coder:32b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i7-14700FCortex-X925
Cores2820
RAM128 GB122 GB
GPUNVIDIA GeForce RTX 5080Device 2e12
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

Qwen3-Next-80B:80B qwen2.5-coder:32b
Tokens/sec29.19.5
First chunk815 ms394 ms
TTFT769 ms395 ms
Load time56.9 s72.1 s
Memory usage61.7 GB26.5 GB
Memory %48%22%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

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

qwen2.5-coder:32b

Speed
9/50
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: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-Next-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