Back to leaderboard

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

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

ornith-1.5-9b_hybrid-imatrix

LM-STUDIO GGUF

qwen35 · F16

Not Rec.

Aug 23, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
87 vs 66
Hardware Fit
85 vs 51
Quality Score
88 vs 73

Hardware

qwen3-coder-30b-a3… ornith-1.5-9b_hybr…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7C37
CPUApple M1 ProAMD Ryzen 9 3900X 12-Core Processor
Cores1024
RAM32 GB128 GB
GPUApple M1 ProIntel(R) Arc(TM) Pro B70 Graphics
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-coder-30b-a3… ornith-1.5-9b_hybr…
Tokens/sec45.75.4
First chunk17 ms39 ms
TTFT390 ms940 ms
Load timeN/AN/A
Memory usage22.4 GB10.7 GB
Memory %70%8%

HW Fit Score Breakdown

qwen3-coder-30b-a3b-ins…

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

ornith-1.5-9b_hybrid-im…

Speed
5/50
TTFT
16/20
Memory
30/30

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

ornith-1.5-9b_hybrid-im…

Reasoning
14/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-coder-30b-a3… details | View ornith-1.5-9b_hybr… 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