Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jun 25, 2026 · Cortex-X925

Global Score
59 vs 92
Hardware Fit
63 vs 86
Quality Score
58 vs 95

Hardware

qwen3.8-27b-mlx gpt-oss:20b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M5 MaxCortex-X925
Cores1820
RAM64 GB122 GB
GPUApple M5 MaxDevice 2e12
OSmacOS 27.0Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.8-27b-mlx gpt-oss:20b
Tokens/sec18.360.7
First chunk4 ms542 ms
TTFT530 ms3.2 s
Load timeN/A12.0 s
Memory usage38.5 GB12.0 GB
Memory %60%10%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

gpt-oss:20b

Speed
50/50
TTFT
6/20
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

gpt-oss:20b

Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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