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

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

Global Score
78 vs 90
Hardware Fit
56 vs 96
Quality Score
87 vs 87

Hardware

qwen3.8-27b-uncens… qwen3-coder:30b
MachineSystem manufacturerASUS
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ Ultra 9 285K
Cores1624
RAM31 GB47 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… qwen3-coder:30b
Tokens/sec7.0207.9
First chunk19 ms513 ms
TTFT1.2 s513 ms
Load timeN/A4.9 s
Memory usage15.6 GB20.5 GB
Memory %50%43%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

qwen3-coder:30b

Speed
50/50
TTFT
20/20
Memory
26/30

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

qwen3-coder:30b

Reasoning
16/20
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
View qwen3.8-27b-uncens… details | View qwen3-coder:30b 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