Back to leaderboard

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

LM-STUDIO GGUF

qwen35 · 27B

Excellent

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

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
81 vs 79
Hardware Fit
64 vs 57
Quality Score
88 vs 89

Hardware

qwen3.8-27b-uncens… qwen3.5:27b
MachineSystem manufacturerAZW GTR Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1632
RAM31 GB125 GB
GPUNavi 44 [Radeon RX 9060 XT]Integrated / Apple Silicon
OSUbuntu 26.04.1 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.8-27b-uncens… qwen3.5:27b
Tokens/sec11.710.7
First chunk50 ms341 ms
TTFT1.1 s341 ms
Load timeN/A10.2 s
Memory usage15.8 GB39.7 GB
Memory %51%32%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

Speed
19/50
TTFT
20/20
Memory
25/30

qwen3.5:27b

Speed
9/50
TTFT
20/20
Memory
28/30

Quality

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5:27b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.8-27b-uncens… details | View qwen3.5:27b 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