gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
Global Score
93 vs 81
Hardware Fit
100 vs 63
Quality Score
90 vs 88
Hardware
gemma4:e2b qwen3.5-35b-a3b-t4…
MachineMicrosoft WSLDell Inc. PowerEdge R820
CPUAMD Ryzen 5 5500Intel Xeon® E5-4650 v2
Cores1280
RAM8 GB256 GB
GPUIntegrated / UnknownMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSUbuntu 26.04.1 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modeunknownbalanced
Performance
gemma4:e2b qwen3.5-35b-a3b-t4…
Tokens/sec141.217.2
First chunk94 ms845 ms
TTFT1.6 s845 ms
Load time18.4 s103.1 s
Memory usage0.2 GB21.9 GB
Memory %3%9%
HW Fit Score Breakdown
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
Memory
30/30
Quality
gemma4:e2b
Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-35b-a3b-t48-c8k…
Reasoning
17/20
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
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