Internlm 20B vs Internlm3 8B Instruct
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Internlm 20B | Internlm3 8B Instruct | |
|---|---|---|
| Parameters | 20B | 8.8B |
| Context | 4K | 33K |
| Architecture | InternLMForCausalLM | InternLM3ForCausalLM |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 1.6K | 89.5K |
| Released | — | Feb 2025 |
VRAM by Quantization: Internlm 20B vs Internlm3 8B Instruct
| Quantization | Bits | Internlm 20B VRAM | Internlm3 8B Instruct VRAM |
|---|---|---|---|
| Q2_K | 3.40 | — | 4.1 GB |
| Q3_K_M | 3.90 | — | 4.7 GB |
| Q3_K_S | 3.50 | — | 4.3 GB |
| Q4_0 | 4.00 | — | 4.8 GB |
| Q4_K_M | 4.80 | — | 5.7 GB |
| Q5_K_M | 5.70 | — | 6.7 GB |
| Q6_K | 6.60 | — | 7.7 GB |
| Q8_0 | 8.00 | — | 9.2 GB |
Verdict
Internlm3 8B Instruct supports a longer context window (33K tokens). Internlm3 8B Instruct is the more widely downloaded of the two.
Frequently Asked Questions
- Which has a longer context window, Internlm 20B or Internlm3 8B Instruct?
Internlm 20B supports 4,096 tokens and Internlm3 8B Instruct supports 32,768 tokens.
- What is the difference between Internlm 20B and Internlm3 8B Instruct?
Internlm 20B is a 20B model from InternLM (InternLM family), while Internlm3 8B Instruct is a 8.8B model from InternLM (InternLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.