Back to leaderboard

deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor

Global Score
47 vs 87
Hardware Fit
51 vs 75
Quality Score
45 vs 92

Hardware

deepseek-r1:70b gemma4:latest
MachineNVIDIA NVIDIA_DGX_SparkMicro-Star International Co., Ltd. MS-7E47
CPUCortex-X925AMD Ryzen 9 9950X 16-Core Processor
Cores2032
RAM122 GB125 GB
GPUDevice 2e12AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modeperformancebalanced

Performance

deepseek-r1:70b gemma4:latest
Tokens/sec4.742.4
First chunk557 ms472 ms
TTFT557 ms3.8 s
Load time52.6 s0.3 s
Memory usage49.5 GB12.3 GB
Memory %41%10%

HW Fit Score Breakdown

deepseek-r1:70b

Speed
4/50
TTFT
20/20
Memory
27/30

gemma4:latest

Speed
40/50
TTFT
5/20
Memory
30/30

Quality

deepseek-r1:70b

Reasoning
3/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
10/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

gemma4:latest

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
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