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

ornith-1.5-9b_hybrid-imatrix

LM-STUDIO GGUF

qwen35 · F16

Not Rec.

Aug 23, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
81 vs 66
Hardware Fit
64 vs 51
Quality Score
88 vs 73

Hardware

qwen3.8-27b-uncens… ornith-1.5-9b_hybr…
MachineSystem manufacturerMicro-Star International Co., Ltd. MS-7C37
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 9 3900X 12-Core Processor
Cores1624
RAM31 GB128 GB
GPUNavi 44 [Radeon RX 9060 XT]Intel(R) Arc(TM) Pro B70 Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… ornith-1.5-9b_hybr…
Tokens/sec11.75.4
First chunk50 ms39 ms
TTFT1.1 s940 ms
Load timeN/AN/A
Memory usage15.8 GB10.7 GB
Memory %51%8%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

ornith-1.5-9b_hybrid-im…

Speed
5/50
TTFT
16/20
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

ornith-1.5-9b_hybrid-im…

Reasoning
14/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate 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