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

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
81 vs 77
Hardware Fit
64 vs 53
Quality Score
88 vs 87

Hardware

qwen3.8-27b-uncens… qwen3.5:35b
MachineSystem manufacturerASUS
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ i5-14600KF
Cores1620
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… qwen3.5:35b
Tokens/sec11.716.0
First chunk50 ms719 ms
TTFT1.1 s719 ms
Load timeN/A17.8 s
Memory usage15.8 GB25.0 GB
Memory %51%79%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

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

qwen3.5:35b

Reasoning
17/20
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
View qwen3.8-27b-uncens… details | View qwen3.5:35b 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