qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
59 vs 83
Hardware Fit
63 vs 64
Quality Score
58 vs 91
Hardware
qwen3.8-27b-mlx gpt-oss:120b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M5 MaxCortex-X925
Cores1820
RAM64 GB122 GB
GPUApple M5 MaxDevice 2e12
OSmacOS 27.0Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3.8-27b-mlx gpt-oss:120b
Tokens/sec18.328.6
First chunk4 ms422 ms
TTFT530 ms2.5 s
Load timeN/A9.9 s
Memory usage38.5 GB60.1 GB
Memory %60%49%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
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:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest