qwen/qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q6_K
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
72 vs 81
Hardware Fit
35 vs 100
Quality Score
88 vs 73
Hardware
qwen/qwen3.5-35b-a3b gemma3n:latest
MachineSystem manufacturerSupermicro AS -2015HS-TNR
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD EPYC 9654P 96-Core Processor
Cores1664
RAM32 GB128 GB
GPUAMD Radeon RX 9060 XTGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 24.04.3 LTS
Archx64x64
Power Modebalancedperformance
Performance
qwen/qwen3.5-35b-a3b gemma3n:latest
Tokens/sec8.3108.7
First chunk32 ms333 ms
TTFT2.0 s333 ms
Load timeN/A4.5 s
Memory usage28.9 GB8.6 GB
Memory %91%7%
HW Fit Score Breakdown
qwen/qwen3.5-35b-a3b
Speed
13/50
TTFT
17/20
Memory
5/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
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
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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