qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Aug 20, 2026 · Apple M4 Max
qwen3-coder-next:latest
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
96 vs 82
Hardware Fit
95 vs 71
Quality Score
96 vs 87
Hardware
qwen3-30b-a3b-thin… qwen3-coder-next:l…
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395
Cores1632
RAM128 GB125 GB
GPUApple M4 MaxAMD Radeon 8060S
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3-30b-a3b-thin… qwen3-coder-next:l…
Tokens/sec112.834.5
First chunk21 ms262 ms
TTFT1.5 s262 ms
Load time3.5 s16.4 s
Memory usage0.0 GB56.8 GB
Memory %0%46%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
qwen3-coder-next:latest
Speed
34/50
TTFT
20/20
Memory
17/30
Quality
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder-next:latest
Reasoning
18/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
13/15
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