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

google/gemma-4-26b-a4b-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
78 vs 93
Hardware Fit
56 vs 96
Quality Score
87 vs 92

Hardware

qwen3.8-27b-uncens… google/gemma-4-26b…
MachineSystem manufacturerMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… google/gemma-4-26b…
Tokens/sec7.0109.7
First chunk19 ms29 ms
TTFT1.2 s156 ms
Load timeN/AN/A
Memory usage15.6 GB14.6 GB
Memory %50%47%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

google/gemma-4-26b-a4b-…

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

google/gemma-4-26b-a4b-…

Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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