qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
59 vs 65
Hardware Fit
63 vs 96
Quality Score
58 vs 52
Hardware
qwen3.8-27b-mlx richardyoung/qwyth…
MachineMacBook ProMac mini
CPUApple M5 MaxApple M4 Pro
Cores1812
RAM64 GB24 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 27.0macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx richardyoung/qwyth…
Tokens/sec18.325.3
First chunk4 ms397 ms
TTFT530 ms397 ms
Load timeN/A6.3 s
Memory usage38.5 GB8.3 GB
Memory %60%34%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
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
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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