deepseek-r1:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 27, 2026 · Cortex-X925
internlm2_5-1_8b-chat
LM-STUDIO GGUFinternlm2 · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
47 vs 55
Hardware Fit
51 vs 60
Quality Score
45 vs 53
Hardware
deepseek-r1:70b internlm2_5-1_8b-c…
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20BUS00700
CPUCortex-X925Intel Core™ i5-5300U
Cores204
RAM122 GB16 GB
GPUDevice 2e12Intel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modeperformancebalanced
Performance
deepseek-r1:70b internlm2_5-1_8b-c…
Tokens/sec4.76.6
First chunk557 ms3037 ms
TTFT557 ms3.0 s
Load time52.6 sN/A
Memory usage49.5 GB1.1 GB
Memory %41%7%
HW Fit Score Breakdown
deepseek-r1:70b
Speed
4/50
TTFT
20/20
Memory
27/30
internlm2_5-1_8b-chat
Speed
23/50
TTFT
16/20
Memory
21/30
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
internlm2_5-1_8b-chat
Reasoning
10/20
Coding
9/20
Instruction
14/20
Structured
10/15
Math
5/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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