Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

qwen3.8-27b-nvfp4-budget

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
59 vs 89
Hardware Fit
63 vs 96
Quality Score
58 vs 86

Hardware

qwen3.8-27b-mlx qwen3.8-27b-nvfp4-…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E51
CPUApple M5 MaxAMD Ryzen 7 9700X 8-Core Processor
Cores1816
RAM64 GB31 GB
GPUApple M5 MaxNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 27.0Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx qwen3.8-27b-nvfp4-…
Tokens/sec18.348.5
First chunk4 ms39 ms
TTFT530 ms283 ms
Load timeN/AN/A
Memory usage38.5 GB13.7 GB
Memory %60%44%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

qwen3.8-27b-nvfp4-budget

Speed
50/50
TTFT
20/20
Memory
26/30

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

qwen3.8-27b-nvfp4-budget

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.8-27b-mlx details | View qwen3.8-27b-nvfp4-… 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