Back to leaderboard

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

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

Global Score
82 vs 93
Hardware Fit
94 vs 93
Quality Score
77 vs 93

Hardware

glm-4.7-flash:latest gemma-4-26b-a4b-it…
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 7800X3D 8-Core Processor
Cores3216
RAM125 GB31 GB
GPURadeon 8060SNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

glm-4.7-flash:latest gemma-4-26b-a4b-it…
Tokens/sec47.6166.9
First chunk200 ms6 ms
TTFT200 ms113 ms
Load time7.3 sN/A
Memory usage37.7 GB16.2 GB
Memory %30%53%

HW Fit Score Breakdown

glm-4.7-flash:latest

Speed
44/50
TTFT
20/20
Memory
30/30

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
23/30

Quality

glm-4.7-flash:latest

Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

gemma-4-26b-a4b-it-qat

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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