qwen3.5:35b-a3b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 22, 2026 · AMD RYZEN AI MAX+ 395
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
88 vs 46
Hardware Fit
90 vs 93
Quality Score
87 vs 26
Hardware
qwen3.5:35b-a3b gemma3:4b
MachineAZW GTR ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD RYZEN AI MAX+ 395Cortex-A78AE
Cores326
RAM125 GB7 GB
GPURadeon 8060SIntegrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3.5:35b-a3b gemma3:4b
Tokens/sec42.014.9
First chunk243 ms2204 ms
TTFT243 ms2.2 s
Load time9.7 s2.0 s
Memory usage32.1 GB2.6 GB
Memory %26%35%
HW Fit Score Breakdown
qwen3.5:35b-a3b
Speed
40/50
TTFT
20/20
Memory
30/30
gemma3:4b
Speed
45/50
TTFT
19/20
Memory
29/30
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
gemma3:4b
Reasoning
11/20
Coding
11/20
Instruction
0/20
Structured
0/15
Math
4/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor
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