unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Apr 21, 2026 · Apple M2 Max

Global Score

82 vs 71

Hardware Fit

88 vs 92

Quality Score

80 vs 62

Hardware

unsloth-phi-4 qwen3.5-35b-a3b-un…

MachineMac miniMac Studio

CPUApple M4 ProApple M2 Max

Cores1412

RAM64 GB96 GB

GPUApple M4 ProApple M2 Max

OSmacOS 15.7.4macOS 26.1

Archarm64arm64

Power Modebalancedbalanced

Performance

unsloth-phi-4 qwen3.5-35b-a3b-un…

Tokens/sec27.459.8

First chunk457 ms12 ms

TTFT457 ms2.4 s

Load timeN/AN/A

Memory usage7.7 GB29.7 GB

Memory %12%31%

HW Fit Score Breakdown

unsloth-phi-4

Speed

38/50

TTFT

20/20

Memory

30/30

qwen3.5-35b-a3b-uncenso…

Speed

50/50

TTFT

12/20

Memory

30/30

Quality

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

qwen3.5-35b-a3b-uncenso…

Reasoning

18/20

Coding

8/20

Instruction

13/20

Structured

6/15

Math

12/15

Multilingual

5/10

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

View unsloth-phi-4 details | View qwen3.5-35b-a3b-un… 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