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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
84 vs 62
Hardware Fit
81 vs 77
Quality Score
85 vs 55

Hardware

qwen3.8-27b-uncens… google/gemma-4-e4b
MachineGigabyte Technology Co., Ltd. X570 AORUS PROLENOVO 82JQ
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD Ryzen 7 5800H
Cores1216
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 5070 TiNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.8-27b-uncens… google/gemma-4-e4b
Tokens/sec18.327.6
First chunk9 ms23 ms
TTFT522 ms480 ms
Load time7.7 sN/A
Memory usage14.9 GB13.2 GB
Memory %47%83%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

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

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

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

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View qwen3.8-27b-uncens… details | View google/gemma-4-e4b 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