Back to leaderboard

qwen3:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
86 vs 55
Hardware Fit
98 vs 100
Quality Score
81 vs 36

Hardware

qwen3:30b phi-3.5-mini-instr…
MachineASUSMacBook Air
CPUIntel Core™ Ultra 9 285KApple M4
Cores2410
RAM47 GB32 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:30b phi-3.5-mini-instr…
Tokens/sec204.843.4
First chunk96 ms359 ms
TTFT674 ms359 ms
Load time5.2 sN/A
Memory usage20.5 GB2.0 GB
Memory %43%6%

HW Fit Score Breakdown

qwen3:30b

Speed
50/50
TTFT
20/20
Memory
28/30

phi-3.5-mini-instruct

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

Quality

qwen3:30b

Reasoning
16/20
Coding
12/20
Instruction
17/20
Structured
12/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

phi-3.5-mini-instruct

Reasoning
11/20
Coding
4/20
Instruction
7/20
Structured
1/15
Math
7/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate
View qwen3:30b details | View phi-3.5-mini-instr… 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