Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

gemma-4-e4b-it@q5_k_xl

LM-STUDIO GGUF

gemma4 · Q5_K_XL

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
59 vs 77
Hardware Fit
63 vs 59
Quality Score
58 vs 84

Hardware

qwen3.8-27b-mlx gemma-4-e4b-it@q5_…
MachineMacBook ProDocker Container
CPUApple M5 MaxIntel Gen Intel® Core™ i9-11900H
Cores1816
RAM64 GB15 GB
GPUApple M5 MaxTigerLake-H GT1 [UHD Graphics]
OSmacOS 27.0Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.8-27b-mlx gemma-4-e4b-it@q5_…
Tokens/sec18.39.3
First chunk4 ms51 ms
TTFT530 ms3.4 s
Load timeN/A12.2 s
Memory usage38.5 GB0.0 GB
Memory %60%0%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

gemma-4-e4b-it@q5_k_xl

Speed
17/50
TTFT
12/20
Memory
30/30

Quality

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

gemma-4-e4b-it@q5_k_xl

Reasoning
15/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.8-27b-mlx details | View gemma-4-e4b-it@q5_… 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