qwen/qwen3-30b-a3b-2507
LM-STUDIO GGUFqwen3moe · 30B · Q3_K_L
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
88 vs 65
Hardware Fit
87 vs 96
Quality Score
89 vs 52
Hardware
qwen/qwen3-30b-a3b… richardyoung/qwyth…
MachineASUSMac mini
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M4 Pro
Cores1612
RAM31 GB24 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M4 Pro
OScachyos rollingmacOS 15.6.1
Archx64arm64
Power Modeperformancebalanced
Performance
qwen/qwen3-30b-a3b… richardyoung/qwyth…
Tokens/sec103.025.3
First chunk3 ms397 ms
TTFT184 ms397 ms
Load timeN/A6.3 s
Memory usage20.1 GB8.3 GB
Memory %66%34%
HW Fit Score Breakdown
qwen/qwen3-30b-a3b-2507
Speed
50/50
TTFT
20/20
Memory
17/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
qwen/qwen3-30b-a3b-2507
Reasoning
18/20
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: Adequate Multilingual: Strong
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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