qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_S
Apr 20, 2026 · Apple M2 Max
qwen3.8-9b-heretic-uncensored-nvfp4
LM-STUDIO GGUFqwen35 · 9B · Q8_0
Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
82 vs 82
Hardware Fit
80 vs 100
Quality Score
83 vs 74
Hardware
qwen3.6-35b-a3b qwen3.8-9b-heretic…
MachineMac StudioMicro-Star International Co., Ltd. MS-7E51
CPUApple M2 MaxAMD Ryzen 7 9700X 8-Core Processor
Cores1216
RAM96 GB31 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.6-35b-a3b qwen3.8-9b-heretic…
Tokens/sec55.2130.1
First chunk4 ms20 ms
TTFT30.0 s99 ms
Load timeN/AN/A
Memory usage30.3 GB6.5 GB
Memory %32%21%
HW Fit Score Breakdown
qwen3.6-35b-a3b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3.8-9b-heretic-unce…
Speed
50/50
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
qwen3.8-9b-heretic-unce…
Reasoning
14/20
Coding
14/20
Instruction
13/20
Structured
14/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate 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