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

qwen3.6:35b-a3b

OLLAMA GGUF

qwen35moe · 35.5B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
81 vs 86
Hardware Fit
64 vs 87
Quality Score
88 vs 86

Hardware

qwen3.8-27b-uncens… qwen3.6:35b-a3b
MachineSystem manufacturerGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ i5-14400F
Cores1616
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 5060 Ti
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… qwen3.6:35b-a3b
Tokens/sec11.759.5
First chunk50 ms380 ms
TTFT1.1 s380 ms
Load timeN/A24.6 s
Memory usage15.8 GB20.9 GB
Memory %51%66%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

qwen3.6:35b-a3b

Speed
50/50
TTFT
20/20
Memory
17/30

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

qwen3.6:35b-a3b

Reasoning
16/20
Coding
17/20
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 qwen3.6:35b-a3b 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