phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 3, 2026 · Apple M4

Global Score

28 vs 55

Hardware Fit

66 vs 87

Quality Score

11 vs 41

Hardware

phi-1_5 qwen3.5-0.8b-mlx

MachineLENOVO 20BUS00700MacBook Air

CPUIntel Core™ i5-5300UApple M4

Cores410

RAM16 GB32 GB

GPUIntel(R) HD Graphics 5500Apple M4

OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

phi-1_5 qwen3.5-0.8b-mlx

Tokens/sec6.968.2

First chunk3040 ms3268 ms

TTFT3.0 s3.3 s

Load timeN/AN/A

Memory usage1.4 GB0.6 GB

Memory %9%2%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

qwen3.5-0.8b-mlx

Speed

50/50

TTFT

13/20

Memory

24/30

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

qwen3.5-0.8b-mlx

Reasoning

8/20

Coding

1/20

Instruction

12/20

Structured

12/15

Math

3/15

Multilingual

5/10

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

View phi-1_5 details | View qwen3.5-0.8b-mlx 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