adityakale/kotakneo
OLLAMA GGUFAug 5, 2026 · AMD RYZEN AI MAX+ 395
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
77 vs 84
Hardware Fit
100 vs 97
Quality Score
67 vs 79
Hardware
adityakale/kotakneo qwen3:8b
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Core™ Ultra 9 285K
Cores3224
RAM125 GB47 GB
GPURadeon 8060SNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
adityakale/kotakneo qwen3:8b
Tokens/sec81.2208.0
First chunk183 ms82 ms
TTFT183 ms1.3 s
Load time2.5 s1.5 s
Memory usage17.8 GB9.6 GB
Memory %14%20%
HW Fit Score Breakdown
adityakale/kotakneo
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
Quality
adityakale/kotakneo
Reasoning
11/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate 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