Written by Jakub Rusinowski · Last updated January 15, 2025
Model library → InternLM 3 → InternLM 3 20B Instruct
A powerful mid-size bilingual model. Exceptional at long-form document understanding, scientific reasoning, and code generation in both Chinese and English contexts.
InternLM 3 20B Instruct needs about 13 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 20 Billion |
| Context window | 32,768 |
| Architecture | Dense |
| Provider | Shanghai AI Lab |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 32 GB |
| Record updated | 2025-01-15 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 6.6 GB | 7.4 GB | ~83 tok/s (est.) | Fits comfortably |
| Q3_K_M | 8.5 GB | 9.3 GB | ~69 tok/s (est.) | Fits comfortably |
| Q4_K_M | 12.1 GB | 12.9 GB | ~52 tok/s (est.) | Fits comfortably |
| Q5_K_M | 14.2 GB | 15.0 GB | ~45 tok/s (est.) | Fits comfortably |
| Q6_K | 16.4 GB | 17.2 GB | ~40 tok/s (est.) | Fits comfortably |
| Q8_0 | 21.3 GB | 22.1 GB | ~32 tok/s (est.) | Tight fit |
| F16 | 40.0 GB | 40.8 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
Want the memory numbers alone, at every quantization level and your own context length? Use the InternLM 3 20B Instruct VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs InternLM 3 20B Instruct is the AMD Radeon RX 9060 XT 16GB (16 GB).
Install Ollama, then run:
ollama run internlm3:20bWeights on Hugging Face: internlm/internlm3-20b-instruct.
Best for: bilingual, document analysis, research, complex reasoning.
← All InternLM 3 models | VRAM calculator | Build a PC for this model | Check your own hardware