Internlm 7B vs Internlm Chat 20B

Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.

Internlm 7B

InternLM · 7B

Chat
Internlm Chat 20B

InternLM · 20B

Chat

Specifications

Internlm 7BInternlm Chat 20B
Parameters7B20B
Context2K4K
ArchitectureInternLMForCausalLMInternLMForCausalLM
LicenseApache 2.0
Downloads1.8K992
Released

VRAM by Quantization: Internlm 7B vs Internlm Chat 20B

QuantizationBitsInternlm 7B VRAMInternlm Chat 20B VRAM
FP1616.0015.4 GB42.8 GB

Verdict

Internlm 7B needs less VRAM at FP16 (15.4 GB vs 42.8 GB), so it fits on smaller GPUs. Internlm Chat 20B supports a longer context window (4K tokens). Internlm 7B is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Internlm 7B or Internlm Chat 20B?

At FP16, Internlm 7B needs 15.4 GB and Internlm Chat 20B needs 42.8 GB, so Internlm 7B is the lighter option to run locally.

Which has a longer context window, Internlm 7B or Internlm Chat 20B?

Internlm 7B supports 2,048 tokens and Internlm Chat 20B supports 4,096 tokens.

What is the difference between Internlm 7B and Internlm Chat 20B?

Internlm 7B is a 7B model from InternLM (InternLM family), while Internlm Chat 20B is a 20B model from InternLM (InternLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.