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

hf.co/unsloth/gemma-4-E2B-it-GGUF:UD-Q8_K_XL

OLLAMA GGUF

gemma4 · 4.65B · unknown

Excellent

Aug 23, 2026 · Apple M1 Pro

Global Score
83 vs 84
Hardware Fit
86 vs 99
Quality Score
81 vs 77

Hardware

zai-org/glm-4.7-fl… hf.co/unsloth/gemm…
MachineASUSMacBook Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M1 Pro
Cores1610
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M1 Pro
OScachyos rollingmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

zai-org/glm-4.7-fl… hf.co/unsloth/gemm…
Tokens/sec102.948.0
First chunk5 ms167 ms
TTFT153 ms167 ms
Load timeN/A4.7 s
Memory usage20.8 GB5.3 GB
Memory %68%33%

HW Fit Score Breakdown

zai-org/glm-4.7-flash

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

hf.co/unsloth/gemma-4-E…

Speed
50/50
TTFT
20/20
Memory
29/30

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

hf.co/unsloth/gemma-4-E…

Reasoning
12/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
8/15
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 hf.co/unsloth/gemm… 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