Internlm 20B — Hardware Requirements & GPU Compatibility
Chat
InternLM-20B is a 20-billion-parameter base language model released by the Shanghai Artificial Intelligence Laboratory with SenseTime, the Chinese University of Hong Kong, and Fudan University, pretrained on over 2.3 trillion tokens of English, Chinese, and code data. It is a pretrained model, not instruction-tuned; a separate InternLM-20B-Chat checkpoint underwent additional SFT and RLHF. Unlike typical 13B models that use 32-40 layers, it uses an unusually deep 60-layer architecture, which the card credits for its strong language, reasoning, and comprehension scores against Llama-13B, Llama2-13B, and Baichuan2-13B, approaching some 33B-70B models on several benchmarks. As an early open Chinese LLM from 2023, it predates today's more capable open models of similar size, and it needs a high-end consumer GPU or multi-GPU setup to run comfortably. Context length is 4,096 tokens, though the card states it can support 16,384 tokens through inference-time extrapolation. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in September 2023.
Internlm 20B runs on a 48 GB+ Mac or a workstation GPU
Best local pick → Mac Studio M5 Max (48 GB) · BF16 · 45.3 GB · ~10 tok/s
Macs from 48 GB (BF16 · ~10 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Internlm 20B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve internlm/internlm-20b --max-model-len 4096vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on H100 (80 GB) (34 GB headroom) · BF16
- Generation speed
- ~51 tok/s
- generation speed
- Cost per 1M output tokens
- $14.68
- per 1M output tokens
How Much VRAM Does Internlm 20B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 42.8 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 42.8 GB |
Selected BF16
Brain floating point 1645.3GBat 4K context
- Weights
- 40.0 GB
- KV cache
- 5.0 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 21.3 GB more
Or .
Which Hardware Can Run Internlm 20B?
BF16 · 42.8 GBInternlm 20B (BF16) requires 42.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 56+ GB is recommended. Using the full 4K context window can add up to 2.5 GB, bringing total usage to 45.3 GB. No consumer GPU has enough memory. 67 devices with unified memory can run Internlm 20B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (64 GB).
48 GB
48 GB tier →fits · 2.7 GB free · up to 4K ctx
2 Mac classes · 1 device family
M5 Max48 GB~10Simulate output on Mac Studio M5 Max (48 GB)M5 Pro48 GB~5Simulate output on Mac Mini M5 Pro (48 GB)Snapdragon X2 Elite Extreme (X2E-96-100)~4Simulate output on Snapdragon X2 Elite Extreme Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
How good is Internlm 20B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 6 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- BIG-Bench Hard
Epoch AI · Sep 2023Lab-reported
Lab-reported52.5%
#19/38 open
- GSM8K
Epoch AI · Sep 2023Lab-reported
Lab-reported62.9%
#23/62 open
- HellaSwag
Epoch AI · Sep 2023Lab-reported
Lab-reported78.1%
#17/47 open
- ARC Challenge
Epoch AI · Sep 2023Lab-reported
Lab-reported81.7%
#12/56 open
- BoolQ
Epoch AI · Sep 2023Lab-reported
Lab-reported87.5%
#4/38 open
- PIQA
Epoch AI · Sep 2023Lab-reported
Lab-reported80.3%
#19/40 open
Alternatives to Internlm 20B
InternLM family · 7 models →Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| InternVL3 5 GPT OSS 20B A4B Preview HFOpenGVLab | — | 13.6 GB | ~180 | same size |
| Tri 21B Thinktrillionlabs | — | 45.1 GB | —needs > 24 GB | same size |
| ERNIE 4.5 21B A3B PTBaidu | — | 13.8 GB | ~254 | same size |
| GPT Neox 20BEleutherAI | — | 13.7 GB | ~48 | same size |
Specifications
- Publisher
- InternLM
- Family
- InternLM
- Parameters
- 20B
- Architecture
- InternLMForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 103,168
- Release Date
- 2023-09-18
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Internlm 20B need?
Internlm 20B requires 42.8 GB of VRAM at BF16. Full 4K context adds up to 2.5 GB (45.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 20B × 16 bits ÷ 8 = 40 GB
KV Cache + Overhead ≈ 2.8 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 5.3 GB (at full 4K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Internlm 20B?
No — Internlm 20B requires at least 42.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Internlm 20B on a Mac?
Yes — Mac Studio M5 Max (48 GB) and 55 other Macs can run Internlm 20B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 42.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Internlm 20B locally?
Yes — Internlm 20B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Internlm 20B?
At BF16, Internlm 20B can reach ~112 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 42.8 × 0.65 = ~121 tok/s
Estimated speed at BF16 (42.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Internlm 20B?
At BF16, the download is about 40.00 GB.
Which GPUs can run Internlm 20B?
No single consumer GPU has enough VRAM to run Internlm 20B at BF16 (42.8 GB). Multi-GPU or professional hardware is required.
Which devices can run Internlm 20B?
67 devices with unified memory can run Internlm 20B at BF16 (42.8 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.