qwen3.5:35b-a3b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 22, 2026 · AMD RYZEN AI MAX+ 395
Gemma4-26B:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
88 vs 92
Hardware Fit
90 vs 100
Quality Score
87 vs 89
Hardware
qwen3.5:35b-a3b Gemma4-26B:26b
MachineAZW GTR ProHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUAMD RYZEN AI MAX+ 395NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores3220
RAM125 GB55 GB
GPURadeon 8060SNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3.5:35b-a3b Gemma4-26B:26b
Tokens/sec42.061.3
First chunk243 ms185 ms
TTFT243 ms185 ms
Load time9.7 s22.9 s
Memory usage32.1 GB16.4 GB
Memory %26%30%
HW Fit Score Breakdown
qwen3.5:35b-a3b
Speed
40/50
TTFT
20/20
Memory
30/30
Gemma4-26B:26b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:35b-a3b
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Gemma4-26B:26b
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
13/15
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