Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

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

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
65 vs 71
Hardware Fit
87 vs 42
Quality Score
56 vs 84

Hardware

qwen2.5:1.5b qwen3:30b-a3b-inst…
MachineShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRBDell Inc. PowerEdge R820
CPUZHAOXIN KaiXian KX-7000 KaiXian KX-7000Intel Xeon® E5-4620 0
Cores864
RAM30 GB256 GB
GPUZX C-1190Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Pro 10.0.26100Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b qwen3:30b-a3b-inst…
Tokens/sec16.84.0
First chunk941 ms2070 ms
TTFT941 ms2.1 s
Load time0.2 s44.5 s
Memory usage1.0 GB17.7 GB
Memory %3%7%

HW Fit Score Breakdown

qwen2.5:1.5b

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

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

Quality

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

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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