Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

glm-4.7-flash-reap-39-i1

LM-STUDIO GGUF

deepseek2 · Q5_K_M

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
66 vs 80
Hardware Fit
40 vs 97
Quality Score
77 vs 73

Hardware

gemma4:31b glm-4.7-flash-reap…
MachineASUSTeK COMPUTER INC. GX10Micro-Star International Co., Ltd. MS-7E51
CPUCortex-X925AMD Ryzen 7 9700X 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

gemma4:31b glm-4.7-flash-reap…
Tokens/sec10.7154.8
First chunk983 ms13 ms
TTFT20.3 s70 ms
Load time8.8 sN/A
Memory usage21.4 GB12.6 GB
Memory %18%41%

HW Fit Score Breakdown

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

glm-4.7-flash-reap-39-i1

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

glm-4.7-flash-reap-39-i1

Reasoning
13/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Adequate
View gemma4:31b details | View glm-4.7-flash-reap… 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