qwen/qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q6_K
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
72 vs 85
Hardware Fit
35 vs 100
Quality Score
88 vs 78
Hardware
qwen/qwen3.5-35b-a3b gemma4:e2b
MachineSystem manufacturerMicrosoft WSL
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 5 5500
Cores1612
RAM32 GB8 GB
GPUAMD Radeon RX 9060 XTIntegrated / Unknown
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedunknown
Performance
qwen/qwen3.5-35b-a3b gemma4:e2b
Tokens/sec8.3139.2
First chunk32 ms51 ms
TTFT2.0 s51 ms
Load timeN/A28.5 s
Memory usage28.9 GB0.2 GB
Memory %91%3%
HW Fit Score Breakdown
qwen/qwen3.5-35b-a3b
Speed
13/50
TTFT
17/20
Memory
5/30
gemma4:e2b
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
gemma4:e2b
Reasoning
13/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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