zai-org/glm-4.7-flash

LM-STUDIO GGUF

deepseek2 · 30B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score

82 vs 82

Hardware Fit

83 vs 88

Quality Score

81 vs 80

Hardware

zai-org/glm-4.7-fl… unsloth-phi-4

MachineGMKtec EVO-X3Mac mini

CPUAMD RYZEN AI MAX+ 395Apple M4 Pro

Cores3214

RAM120 GB64 GB

GPUAMD Radeon(TM) 8060S GraphicsApple M4 Pro

OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.7.4

Archx64arm64

Power Modebalancedbalanced

Performance

zai-org/glm-4.7-fl… unsloth-phi-4

Tokens/sec36.727.4

First chunk29 ms457 ms

TTFT131 ms457 ms

Load time82.7 sN/A

Memory usage47.4 GB7.7 GB

Memory %40%12%

HW Fit Score Breakdown

zai-org/glm-4.7-flash

Speed

35/50

TTFT

20/20

Memory

28/30

unsloth-phi-4

Speed

38/50

TTFT

20/20

Memory

30/30

Quality

zai-org/glm-4.7-flash

Reasoning

14/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

10/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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 zai-org/glm-4.7-fl… 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