Back to leaderboard

qwen3-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
70 vs 65
Hardware Fit
39 vs 87
Quality Score
83 vs 56

Hardware

qwen3-next-80b-t48… qwen2.5:1.5b
MachineDell Inc. PowerEdge R820Shanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUIntel Xeon® E5-4620 0ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores648
RAM256 GB30 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterZX C-1190
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-next-80b-t48… qwen2.5:1.5b
Tokens/sec3.016.8
First chunk3265 ms941 ms
TTFT3.3 s941 ms
Load time82.1 s0.2 s
Memory usage46.9 GB1.0 GB
Memory %18%3%

HW Fit Score Breakdown

qwen3-next-80b-t48:latest

Speed
3/50
TTFT
6/20
Memory
30/30

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

qwen3-next-80b-t48:latest

Reasoning
18/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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