Back to leaderboard

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Good

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

adityakale/kotakneo

OLLAMA GGUF
Good

Aug 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
78 vs 77
Hardware Fit
56 vs 100
Quality Score
87 vs 67

Hardware

qwen3.8-27b-uncens… adityakale/kotakneo
MachineSystem manufacturerAZW GTR Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1632
RAM31 GB125 GB
GPUNavi 44 [Radeon RX 9060 XT]Radeon 8060S
OSUbuntu 26.04.1 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformancelow-power

Performance

qwen3.8-27b-uncens… adityakale/kotakneo
Tokens/sec7.081.2
First chunk19 ms183 ms
TTFT1.2 s183 ms
Load timeN/A2.5 s
Memory usage15.6 GB17.8 GB
Memory %50%14%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

Speed
11/50
TTFT
20/20
Memory
25/30

adityakale/kotakneo

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8-27b-uncensored-…

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: Adequate Multilingual: Strong

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
View qwen3.8-27b-uncens… details | View adityakale/kotakneo details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest