qwen/qwen3-coder-30b
LM-STUDIO GGUFqwen3moe · 30B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
85 vs 88
Hardware Fit
79 vs 94
Quality Score
88 vs 85
Hardware
qwen/qwen3-coder-30b huihui-qwen3.6-35b…
MachineGMKtec EVO-X3Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 5 5600X 6-Core Processor
Cores3212
RAM120 GB47 GB
GPUAMD Radeon(TM) 8060S GraphicsAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Pro 10.0.26300cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
qwen/qwen3-coder-30b huihui-qwen3.6-35b…
Tokens/sec42.339.8
First chunk10 ms3 ms
TTFT707 ms479 ms
Load time167.7 sN/A
Memory usage70.3 GB24.4 GB
Memory %59%52%
HW Fit Score Breakdown
qwen/qwen3-coder-30b
Speed
40/50
TTFT
18/20
Memory
21/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
20/20
Memory
24/30
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
huihui-qwen3.6-35b-a3b-…
Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
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