Back to leaderboard

qwen3-30b-a3b-t16-c32k-instruct:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 18, 2026 · Intel Xeon® E5-2637 v3

mlx-community/Llama-3.2-3B-Instruct-4bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

Global Score
93 vs 74
Hardware Fit
97 vs 100
Quality Score
91 vs 63

Hardware

qwen3-30b-a3b-t16-… mlx-community/Llam…
MachineDell Inc. Precision Tower 7910MacBook Air
CPUIntel Xeon® E5-2637 v3Apple M4
Cores1610
RAM96 GB32 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M4
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-t16-… mlx-community/Llam…
Tokens/sec100.050.6
First chunk1275 ms257 ms
TTFT1.3 s257 ms
Load time23.6 sN/A
Memory usage21.0 GB0.7 GB
Memory %22%2%

HW Fit Score Breakdown

qwen3-30b-a3b-t16-c32k-…

Speed
50/50
TTFT
17/20
Memory
30/30

mlx-community/Llama-3.2…

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

Quality

qwen3-30b-a3b-t16-c32k-…

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

mlx-community/Llama-3.2…

Reasoning
9/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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