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-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Jul 31, 2026 · Intel Core™ i9-14900K

Global Score
81 vs 79
Hardware Fit
64 vs 62
Quality Score
88 vs 86

Hardware

qwen3.8-27b-uncens… qwen3.5:35b-a3b-q4…
MachineSystem manufacturerMicro-Star International Co., Ltd. MS-7D98
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ i9-14900K
Cores1632
RAM31 GB128 GB
GPUNavi 44 [Radeon RX 9060 XT]Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… qwen3.5:35b-a3b-q4…
Tokens/sec11.716.4
First chunk50 ms787 ms
TTFT1.1 s787 ms
Load timeN/A19.3 s
Memory usage15.8 GB21.8 GB
Memory %51%17%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
17/20
Memory
30/30

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-a3b-q4_K_M

Reasoning
17/20
Coding
17/20
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

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