qwen/qwen3-coder-30b
LM-STUDIO GGUFqwen3moe · 30B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
mistralai/magistral-small-2509
LM-STUDIO MLXmistral3 · 24B · 4bit
Mar 4, 2026 · Apple M4
Global Score
85 vs 74
Hardware Fit
79 vs 66
Quality Score
88 vs 78
Hardware
qwen/qwen3-coder-30b mistralai/magistra…
MachineGMKtec EVO-X3MacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM120 GB32 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3-coder-30b mistralai/magistra…
Tokens/sec42.37.9
First chunk10 ms1356 ms
TTFT707 ms1.4 s
Load time167.7 sN/A
Memory usage70.3 GB13.2 GB
Memory %59%41%
HW Fit Score Breakdown
qwen/qwen3-coder-30b
Speed
40/50
TTFT
18/20
Memory
21/30
mistralai/magistral-sma…
Speed
16/50
TTFT
20/20
Memory
30/30
Quality
qwen/qwen3-coder-30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
mistralai/magistral-sma…
Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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