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

unsloth/gemma-4-26b-a4b-it

LM-STUDIO GGUF

gemma4 · 26B · Q3_K_M

Excellent

Apr 5, 2026 · Apple M4

Global Score
78 vs 90
Hardware Fit
56 vs 85
Quality Score
87 vs 92

Hardware

qwen3.8-27b-uncens… unsloth/gemma-4-26…
MachineSystem manufacturerMac mini
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M4
Cores1610
RAM31 GB24 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.8-27b-uncens… unsloth/gemma-4-26…
Tokens/sec7.024.9
First chunk19 ms15 ms
TTFT1.2 s817 ms
Load timeN/AN/A
Memory usage15.6 GB16.8 GB
Memory %50%70%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

unsloth/gemma-4-26b-a4b…

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

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

unsloth/gemma-4-26b-a4b…

Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.8-27b-uncens… details | View unsloth/gemma-4-26… 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