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

lfm2.5:8b

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Excellent

Aug 24, 2026 · Apple M1 Pro

Global Score
90 vs 80
Hardware Fit
97 vs 95
Quality Score
87 vs 73

Hardware

Qwen3.8-27B-UD-Q3_… lfm2.5:8b
MachineMacBook Pro
CPUIntel Gen Intel® Core™ i5-12600KApple M1 Pro
Cores1610
RAM31 GB16 GB
GPUAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

Qwen3.8-27B-UD-Q3_… lfm2.5:8b
Tokens/sec39.098.5
First chunk305 ms167 ms
TTFT305 ms2.5 s
Load time0.0 s3.0 s
Memory usage12.5 GB6.0 GB
Memory %41%37%

HW Fit Score Breakdown

Qwen3.8-27B-UD-Q3_K_XL

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

lfm2.5:8b

Speed
50/50
TTFT
17/20
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

lfm2.5:8b

Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate 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