mistralai/ministral-3-3b
LM-STUDIO GGUFmistral3 · 3B · Q4_K_M
Oct 31, 2026 · AMD RYZEN AI MAX+ 395
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
76 vs 66
Hardware Fit
94 vs 91
Quality Score
68 vs 55
Hardware
mistralai/ministra… qwen3.8-27b-mlx
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M5 Max
Cores3218
RAM120 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
mistralai/ministra… qwen3.8-27b-mlx
Tokens/sec50.233.2
First chunk6 ms7 ms
TTFT726 ms311 ms
Load timeN/AN/A
Memory usage19.6 GB0.5 GB
Memory %16%1%
HW Fit Score Breakdown
mistralai/ministral-3-3b
Speed
46/50
TTFT
18/20
Memory
30/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
mistralai/ministral-3-3b
Reasoning
10/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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