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

qwen3.6:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Apr 17, 2026 · AMD RYZEN AI MAX+ 395

Global Score
65 vs 88
Hardware Fit
87 vs 91
Quality Score
56 vs 87

Hardware

qwen2.5:1.5b qwen3.6:35b-a3b
MachineShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRBAZW GTR Pro
CPUZHAOXIN KaiXian KX-7000 KaiXian KX-7000AMD RYZEN AI MAX+ 395
Cores832
RAM30 GB125 GB
GPUZX C-1190Radeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26100Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

qwen2.5:1.5b qwen3.6:35b-a3b
Tokens/sec16.843.3
First chunk941 ms291 ms
TTFT941 ms291 ms
Load time0.2 s6.2 s
Memory usage1.0 GB32.2 GB
Memory %3%26%

HW Fit Score Breakdown

qwen2.5:1.5b

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

qwen3.6:35b-a3b

Speed
41/50
TTFT
20/20
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

qwen3.6:35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5:1.5b details | View qwen3.6:35b-a3b 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