Back to leaderboard

Qwen3.8-27B-UD-Q3_K_XL

OLLAMA GGUF

llama · 27.3B · Q4_K

Excellent

Aug 23, 2026 · Intel Gen Intel® Core™ i5-12600K

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
90 vs 79
Hardware Fit
97 vs 57
Quality Score
87 vs 89

Hardware

Qwen3.8-27B-UD-Q3_… qwen3.5:27b
Machine—AZW GTR Pro
CPUIntel Gen Intel® Core™ i5-12600KAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1632
RAM31 GB125 GB
GPUAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]Integrated / Apple Silicon
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerperformance

Performance

Qwen3.8-27B-UD-Q3_… qwen3.5:27b
Tokens/sec39.010.7
First chunk305 ms341 ms
TTFT305 ms341 ms
Load time0.0 s10.2 s
Memory usage12.5 GB39.7 GB
Memory %41%32%

HW Fit Score Breakdown

Qwen3.8-27B-UD-Q3_K_XL

Speed
50/50
TTFT
20/20
Memory
27/30

qwen3.5:27b

Speed
9/50
TTFT
20/20
Memory
28/30

Quality

Qwen3.8-27B-UD-Q3_K_XL

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: Strong Multilingual: Strong

qwen3.5:27b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View Qwen3.8-27B-UD-Q3_… details | View qwen3.5:27b 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