deepseek-r1:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 27, 2026 · Cortex-X925
mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
47 vs 53
Hardware Fit
51 vs 99
Quality Score
45 vs 33
Hardware
deepseek-r1:70b mlx-community/Nanb…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
deepseek-r1:70b mlx-community/Nanb…
Tokens/sec4.725.4
First chunk557 ms266 ms
TTFT557 ms266 ms
Load time52.6 sN/A
Memory usage49.5 GB0.0 GB
Memory %41%0%
HW Fit Score Breakdown
deepseek-r1:70b
Speed
4/50
TTFT
20/20
Memory
27/30
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
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
mlx-community/Nanbeige4…
Reasoning
10/20
Coding
7/20
Instruction
1/20
Structured
1/15
Math
11/15
Multilingual
3/10
Reasoning: Adequate Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Weak
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest