Back to leaderboard

deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

gemma4:26b-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
47 vs 85
Hardware Fit
51 vs 80
Quality Score
45 vs 87

Hardware

deepseek-r1:70b gemma4:26b-nvfp4
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB48 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 26.4.1
Archarm64arm64
Power Modeperformancebalanced

Performance

deepseek-r1:70b gemma4:26b-nvfp4
Tokens/sec4.765.7
First chunk557 ms233 ms
TTFT557 ms30.0 s
Load time52.6 s5.0 s
Memory usage49.5 GB15.2 GB
Memory %41%32%

HW Fit Score Breakdown

deepseek-r1:70b

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

gemma4:26b-nvfp4

Speed
50/50
TTFT
0/20
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

gemma4:26b-nvfp4

Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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