phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score

28 vs 89

Hardware Fit

66 vs 97

Quality Score

11 vs 86

Hardware

phi-1_5 qwen/qwen3.6-35b-a3b

MachineLENOVO 20BUS00700MacBook Pro

CPUIntel Core™ i5-5300UApple M5 Max

Cores418

RAM16 GB64 GB

GPUIntel(R) HD Graphics 5500Apple M5 Max

OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 27.0

Archx64arm64

Power Modebalancedbalanced

Performance

phi-1_5 qwen/qwen3.6-35b-a3b

Tokens/sec6.9130.2

First chunk3040 ms5 ms

TTFT3.0 s135 ms

Load timeN/AN/A

Memory usage1.4 GB26.6 GB

Memory %9%42%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

qwen/qwen3.6-35b-a3b

Speed

50/50

TTFT

20/20

Memory

27/30

Quality

phi-1_5

Reasoning

2/20

Coding

2/20

Instruction

3/20

Structured

0/15

Math

2/15

Multilingual

2/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen/qwen3.6-35b-a3b

Reasoning

15/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

12/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

View phi-1_5 details | View qwen/qwen3.6-35b-a3b 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