Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_S

Not Rec.

Apr 20, 2026 · Apple M2 Max

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
82 vs 65
Hardware Fit
80 vs 87
Quality Score
83 vs 56

Hardware

qwen3.6-35b-a3b qwen2.5:1.5b
MachineMac StudioShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M2 MaxZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores128
RAM96 GB30 GB
GPUApple M2 MaxZX C-1190
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.6-35b-a3b qwen2.5:1.5b
Tokens/sec54.716.8
First chunk32 ms941 ms
TTFT30.0 s941 ms
Load timeN/A0.2 s
Memory usage30.3 GB1.0 GB
Memory %32%3%

HW Fit Score Breakdown

qwen3.6-35b-a3b

Speed
50/50
TTFT
0/20
Memory
30/30

qwen2.5:1.5b

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

Quality

qwen3.6-35b-a3b

Reasoning
18/20
Coding
10/20
Instruction
18/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Strong 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
View qwen3.6-35b-a3b details | View qwen2.5:1.5b 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