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

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
90 vs 59
Hardware Fit
97 vs 63
Quality Score
87 vs 58

Hardware

Qwen3.8-27B-UD-Q3_… qwen3.8-27b-mlx
Machine—MacBook Pro
CPUIntel Gen Intel® Core™ i5-12600KApple M5 Max
Cores1618
RAM31 GB64 GB
GPUAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]Apple M5 Max
OSUbuntu 24.04.4 LTSmacOS 27.0
Archx64arm64
Power Modelow-powerbalanced

Performance

Qwen3.8-27B-UD-Q3_… qwen3.8-27b-mlx
Tokens/sec39.018.3
First chunk305 ms4 ms
TTFT305 ms530 ms
Load time0.0 sN/A
Memory usage12.5 GB38.5 GB
Memory %41%60%

HW Fit Score Breakdown

Qwen3.8-27B-UD-Q3_K_XL

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

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View Qwen3.8-27B-UD-Q3_… details | View qwen3.8-27b-mlx 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