Back to leaderboard

zai-org/glm-4.7-flash

LM-STUDIO GGUF

deepseek2 · 30B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
83 vs 62
Hardware Fit
86 vs 77
Quality Score
81 vs 55

Hardware

zai-org/glm-4.7-fl… google/gemma-4-e4b
MachineASUSLENOVO 82JQ
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 7 5800H
Cores1616
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 4090, RaphaelNVIDIA GeForce RTX 3060 Laptop GPU
OScachyos rollingMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modelow-powerbalanced

Performance

zai-org/glm-4.7-fl… google/gemma-4-e4b
Tokens/sec102.927.6
First chunk5 ms23 ms
TTFT153 ms480 ms
Load timeN/AN/A
Memory usage20.8 GB13.2 GB
Memory %68%83%

HW Fit Score Breakdown

zai-org/glm-4.7-flash

Speed
50/50
TTFT
20/20
Memory
16/30

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

Quality

zai-org/glm-4.7-flash

Reasoning
13/20
Coding
19/20
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

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View zai-org/glm-4.7-fl… details | View google/gemma-4-e4b 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