qwen/qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q6_K
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
72 vs 95
Hardware Fit
35 vs 98
Quality Score
88 vs 94
Hardware
qwen/qwen3.5-35b-a3b gpt-oss:20b
MachineSystem manufacturerASUS
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ Ultra 9 285K
Cores1624
RAM32 GB47 GB
GPUAMD Radeon RX 9060 XTNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen/qwen3.5-35b-a3b gpt-oss:20b
Tokens/sec8.3239.9
First chunk32 ms180 ms
TTFT2.0 s616 ms
Load timeN/A4.3 s
Memory usage28.9 GB13.9 GB
Memory %91%29%
HW Fit Score Breakdown
qwen/qwen3.5-35b-a3b
Speed
13/50
TTFT
17/20
Memory
5/30
gpt-oss:20b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
qwen/qwen3.5-35b-a3b
Reasoning
16/20
Coding
19/20
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
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
15/15
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