qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp
LM-STUDIO GGUFqwen35moe · 35B
Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
80 vs 92
Hardware Fit
60 vs 87
Quality Score
88 vs 94
Hardware
qwen3-coder:30b qwen3.6-35b-a3b-cl…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Gen Intel® Core™ i7-12700KAMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM96 GB47 GB
GPUParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
qwen3-coder:30b qwen3.6-35b-a3b-cl…
Tokens/sec14.742.6
First chunk796 ms13 ms
TTFT796 ms3.1 s
Load time0.2 sN/A
Memory usage17.9 GB23.2 GB
Memory %19%49%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
qwen3.6-35b-a3b-claude-…
Speed
50/50
TTFT
12/20
Memory
25/30
Quality
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: Adequate Multilingual: Strong
qwen3.6-35b-a3b-claude-…
Reasoning
20/20
Coding
16/20
Instruction
19/20
Structured
15/15
Math
14/15
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