Back to leaderboard

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jul 29, 2026 · Intel Xeon® E5-2637 v3

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
83 vs 82
Hardware Fit
66 vs 88
Quality Score
90 vs 80

Hardware

qwen3:30b-a3b-inst… unsloth-phi-4
MachineDell Inc. Precision Tower 7910Mac mini
CPUIntel Xeon® E5-2637 v3Apple M4 Pro
Cores1614
RAM96 GB64 GB
GPUNVIDIA GeForce RTX 5060 TiApple M4 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:30b-a3b-inst… unsloth-phi-4
Tokens/sec17.727.4
First chunk1244 ms457 ms
TTFT1.2 s457 ms
Load time20.5 sN/A
Memory usage20.6 GB7.7 GB
Memory %21%12%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

Speed
19/50
TTFT
17/20
Memory
30/30

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3:30b-a3b-inst… details | View unsloth-phi-4 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