Back to leaderboard

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
87 vs 84
Hardware Fit
85 vs 81
Quality Score
88 vs 85

Hardware

qwen3-coder-30b-a3… qwen3.8-27b-uncens…
MachineMacBook ProGigabyte Technology Co., Ltd. X570 AORUS PRO
CPUApple M1 ProAMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM32 GB32 GB
GPUApple M1 ProNVIDIA GeForce RTX 5070 Ti
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-coder-30b-a3… qwen3.8-27b-uncens…
Tokens/sec45.718.3
First chunk17 ms9 ms
TTFT390 ms522 ms
Load timeN/A7.7 s
Memory usage22.4 GB14.9 GB
Memory %70%47%

HW Fit Score Breakdown

qwen3-coder-30b-a3b-ins…

Speed
50/50
TTFT
20/20
Memory
15/30

qwen3.8-27b-uncensored-…

Speed
35/50
TTFT
20/20
Memory
26/30

Quality

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.8-27b-uncensored-…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-coder-30b-a3… details | View qwen3.8-27b-uncens… details

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