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

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

Global Score
81 vs 90
Hardware Fit
64 vs 97
Quality Score
88 vs 87

Hardware

qwen3.8-27b-uncens… qwen3:14b
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M1 Max
Cores1610
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M1 Max
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… qwen3:14b
Tokens/sec11.724.0
First chunk50 ms300 ms
TTFT1.1 s300 ms
Load timeN/A3.6 s
Memory usage15.8 GB13.8 GB
Memory %51%43%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

qwen3:14b

Speed
47/50
TTFT
20/20
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

qwen3:14b

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 qwen3:14b 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