qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
59 vs 81
Hardware Fit
63 vs 80
Quality Score
58 vs 81
Hardware
qwen3.8-27b-mlx devstral-small-2-2…
MachineMacBook ProSystem manufacturer
CPUApple M5 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1816
RAM64 GB31 GB
GPUApple M5 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 27.0Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3.8-27b-mlx devstral-small-2-2…
Tokens/sec18.321.5
First chunk4 ms12 ms
TTFT530 ms212 ms
Load timeN/AN/A
Memory usage38.5 GB15.9 GB
Memory %60%51%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
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
devstral-small-2-24b-in…
Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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