Back to leaderboard

qwen/qwen3-30b-a3b-2507

LM-STUDIO GGUF

qwen3moe · 30B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
90 vs 66
Hardware Fit
86 vs 87
Quality Score
91 vs 57

Hardware

qwen/qwen3-30b-a3b… granite-3.3-2b-ins…
MachineASUSMacBook Air
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M4
Cores1610
RAM31 GB32 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

qwen/qwen3-30b-a3b… granite-3.3-2b-ins…
Tokens/sec157.518.3
First chunk3 ms541 ms
TTFT114 ms541 ms
Load timeN/AN/A
Memory usage21.0 GB4.7 GB
Memory %69%15%

HW Fit Score Breakdown

qwen/qwen3-30b-a3b-2507

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

granite-3.3-2b-instruct

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

qwen/qwen3-30b-a3b-2507

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
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 qwen/qwen3-30b-a3b… 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