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

mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
90 vs 77
Hardware Fit
97 vs 100
Quality Score
87 vs 67

Hardware

Qwen3.8-27B-UD-Q3_… mlx-community/meta…
Machine—Mac mini
CPUIntel Gen Intel® Core™ i5-12600KApple M4 Pro
Cores1614
RAM31 GB64 GB
GPUAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced

Performance

Qwen3.8-27B-UD-Q3_… mlx-community/meta…
Tokens/sec39.054.3
First chunk305 ms277 ms
TTFT305 ms277 ms
Load time0.0 sN/A
Memory usage12.5 GB4.2 GB
Memory %41%7%

HW Fit Score Breakdown

Qwen3.8-27B-UD-Q3_K_XL

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

mlx-community/meta-llam…

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

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

mlx-community/meta-llam…

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View Qwen3.8-27B-UD-Q3_… details | View mlx-community/meta… 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