qwen3.6:35b-a3b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Apr 17, 2026 · AMD RYZEN AI MAX+ 395
qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
88 vs 88
Hardware Fit
91 vs 80
Quality Score
87 vs 91
Hardware
qwen3.6:35b-a3b qwopus3.6-27b-code…
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 7800X3D 8-Core Processor
Cores3216
RAM125 GB31 GB
GPURadeon 8060SNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modelow-powerperformance
Performance
qwen3.6:35b-a3b qwopus3.6-27b-code…
Tokens/sec43.380.8
First chunk291 ms6 ms
TTFT291 ms226 ms
Load time6.2 sN/A
Memory usage32.2 GB24.6 GB
Memory %26%81%
HW Fit Score Breakdown
qwen3.6:35b-a3b
Speed
41/50
TTFT
20/20
Memory
30/30
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
Quality
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
qwopus3.6-27b-coder-com…
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
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