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

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
94 vs 66
Hardware Fit
100 vs 87
Quality Score
91 vs 57

Hardware

qwen3-30b-a3b-t16-… granite-3.3-2b-ins…
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-… granite-3.3-2b-ins…
Tokens/sec116.018.3
First chunk575 ms541 ms
TTFT575 ms541 ms
Load time10.2 sN/A
Memory usage21.0 GB4.7 GB
Memory %22%15%

HW Fit Score Breakdown

qwen3-30b-a3b-t16-c32k-…

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

granite-3.3-2b-instruct

Speed
37/50
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

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3-30b-a3b-t16-… details | View granite-3.3-2b-ins… 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