Back to leaderboard

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
84 vs 88
Hardware Fit
81 vs 77
Quality Score
85 vs 93

Hardware

qwen3.8-27b-uncens… gemma-4-26b-a4b-it…
MachineGigabyte Technology Co., Ltd. X570 AORUS PROASUS
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 5070 TiNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3.8-27b-uncens… gemma-4-26b-a4b-it…
Tokens/sec18.3170.5
First chunk9 ms13 ms
TTFT522 ms121 ms
Load time7.7 sN/A
Memory usage14.9 GB26.0 GB
Memory %47%85%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

Speed
35/50
TTFT
20/20
Memory
26/30

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
7/30

Quality

qwen3.8-27b-uncensored-…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma-4-26b-a4b-it-qat

Reasoning
19/20
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