Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 19, 2026 · Apple M4 Max

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
89 vs 88
Hardware Fit
96 vs 85
Quality Score
86 vs 89

Hardware

qwen3-coder:30b huihui-qwen3.6-35b…
MachineMacBook ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4 MaxAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM64 GB47 GB
GPUApple M4 MaxAD106 [GeForce RTX 4060 Ti]
OSmacOS 26.5.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3-coder:30b huihui-qwen3.6-35b…
Tokens/sec89.937.7
First chunk188 ms18 ms
TTFT188 ms2.9 s
Load time4.0 sN/A
Memory usage30.2 GB26.1 GB
Memory %47%56%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
50/50
TTFT
20/20
Memory
26/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

qwen3-coder:30b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest