qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
Global Score
97 vs 81
Hardware Fit
95 vs 63
Quality Score
98 vs 88
Hardware
qwen3-30b-a3b-thin… qwen3.5-35b-a3b-t4…
MachineMac StudioDell Inc. PowerEdge R820
CPUApple M2 MaxIntel Xeon® E5-4650 v2
Cores1280
RAM96 GB256 GB
GPUApple M2 MaxMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSmacOS 26.1Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… qwen3.5-35b-a3b-t4…
Tokens/sec79.617.2
First chunk11 ms845 ms
TTFT1.7 s845 ms
Load time7.1 s103.1 s
Memory usage0.0 GB21.9 GB
Memory %0%9%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
Memory
30/30
Quality
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-35b-a3b-t48-c8k…
Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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