qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Oct 20, 2026 · Apple M1 Pro
Qwen3-80B:80B
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
84 vs 82
Hardware Fit
78 vs 59
Quality Score
86 vs 92
Hardware
qwen/qwen3.6-35b-a3b Qwen3-80B:80B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M1 ProIntel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M1 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-35b-a3b Qwen3-80B:80B
Tokens/sec49.919.3
First chunk31 ms798 ms
TTFT708 ms798 ms
Load timeN/A38.9 s
Memory usage26.6 GB46.9 GB
Memory %83%74%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
8/30
Qwen3-80B:80B
Speed
26/50
TTFT
20/20
Memory
13/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Qwen3-80B:80B
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest