Qwen3.6-35B-A3B-Q4_K_M:latest
OLLAMA GGUFqwen35moe · 34.7B · Q4_K_M
Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 89
Hardware Fit
87 vs 95
Quality Score
86 vs 87
Hardware
Qwen3.6-35B-A3B-Q4… gemma4:26b
MachineMicro-Star International Co., Ltd. MS-7E51AZW GTR Pro
CPUAMD Ryzen 7 9700X 8-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1632
RAM31 GB125 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsRadeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance
Performance
Qwen3.6-35B-A3B-Q4… gemma4:26b
Tokens/sec92.948.3
First chunk362 ms346 ms
TTFT362 ms346 ms
Load time12.3 s4.4 s
Memory usage20.7 GB36.1 GB
Memory %67%29%
HW Fit Score Breakdown
Qwen3.6-35B-A3B-Q4_K_M:…
Speed
50/50
TTFT
20/20
Memory
17/30
gemma4:26b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
Qwen3.6-35B-A3B-Q4_K_M:…
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:26b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
14/15
Math
13/15
Multilingual
9/10
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