LLMs ·

InternLM2.5 20B Chat

Parameters
20B
Architecture
Dense
Max context
32K tokens
License
internlm
Released
2024-07

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run internlm2:20b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/internlm/internlm2_5-20b-chat-GGUF (opens in a new tab)

ollama run hf.co/internlm/internlm2_5-20b-chat-GGUF

Original weights · Hugging Face

Full-precision files from Shanghai AI Lab, for fine-tuning, vLLM, Transformers.

huggingface.co/internlm/internlm2_5-20b-chat (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Shanghai AI Lab. The weights themselves download from Hugging Face.

github.com/InternLM/InternLM (opens in a new tab)

git clone https://github.com/InternLM/InternLM

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run InternLM2.5 20B Chat

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App Type Opens it as Systems Engine Start
LM Studio Desktop app GGUF macOSWindowsLinux llama.cpp, MLX Open in LM Studio
Ollama CLI + API Ollama library macOSWindowsLinux llama.cpp, MLX 
ollama run internlm2:20b
llama.cpp CLI + API GGUF macOSWindowsLinux llama.cpp 
llama-server -hf internlm/internlm2_5-20b-chat-GGUF:Q4_K_M
Jan Desktop app GGUF macOSWindowsLinux llama.cpp, MLX Open in Jan
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve internlm/internlm2_5-20b-chat
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path internlm/internlm2_5-20b-chat
Docker Model Runner CLI + API GGUF macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/internlm/internlm2_5-20b-chat-GGUF:Q4_K_M
Lemonade Desktop app GGUF macOSWindowsLinux llama.cpp, ONNX Runtime GenAI 
lemonade pull internlm/internlm2_5-20b-chat-GGUF:Q4_K_M
Unsloth Desktop Desktop app GGUF macOSWindowsLinux llama.cpp, MLX, stable-diffusion.cpp Open in Unsloth Desktop
Atomic Chat Desktop app GGUF macOSWindowsLinux llama.cpp, MLX-VLM Open in Atomic Chat
GPT4All Desktop app GGUF macOSWindowsLinux llama.cpp Get GPT4All
KoboldCpp Desktop app GGUF macOSWindowsLinux llama.cpp Get KoboldCpp
Text Generation WebUI Desktop app GGUF macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI
llamafile CLI + API GGUF macOSWindowsLinux llama.cpp Get llamafile
Msty Studio Desktop app GGUF macOSWindowsLinux Ollama, llama.cpp, MLX Open in Msty Studio
Llama (macOS) Desktop app GGUF macOS llama.cpp Open in Llama (macOS)
RecurseChat Desktop app GGUF macOS llama.cpp Open in RecurseChat
node-llama-cpp Library GGUF macOSWindowsLinux llama.cpp Get node-llama-cpp
PocketPal AI Mobile app GGUF iOSAndroid llama.cpp App Store Google Play
ChatterUI Mobile app GGUF Android llama.cpp Download the APK
LLM Farm Mobile app GGUF iOS llama.cpp Not on the App Store or TestFlight for now (checked 2026-11-09).

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 7.9 GB 10.2 GB 15.0 GB GGUF (opens in a new tab)
Q3_K_M Low 9.7 GB 11.9 GB 16.8 GB GGUF (opens in a new tab)
Q4_K_M Good 12.1 GB 14.3 GB 19.2 GB GGUF (opens in a new tab)
Q5_K_M High 14.1 GB 16.3 GB 21.1 GB GGUF (opens in a new tab)
Q6_K High 16.3 GB 18.5 GB 23.3 GB GGUF (opens in a new tab)
Q8_0 Very high 21.1 GB 23.3 GB 28.1 GB GGUF (opens in a new tab)
F16 Full 39.7 GB 41.9 GB 46.8 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for InternLM2.5 20B Chat

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B580 (launch price $249) at Q2_K.

Quality Hardware Quant Memory Speed Runs
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Founders EditionNVIDIA GeForce RTX 5090 Q8_0 24.9 GB / 32.0 GB 56.4 tok/s Runs great
49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. ASUS ROG Strix GeForce RTX 3090 OC Edition 24GB GDDR6XNVIDIA GeForce RTX 3090 Q6_K 19.7 GB / 24.0 GB 40.1 tok/s Runs great
49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Founders EditionNVIDIA GeForce RTX 4090 Q6_K 19.7 GB / 24.0 GB 43.2 tok/s Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 7900 XTX Vapor-X 24GBAMD Radeon RX 7900 XTX Q5_K_M 17.5 GB / 24.0 GB 42.2 tok/s Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 4070 Ti SUPER Q4_K_M 15.1 GB / 16.0 GB 41.5 tok/s Runs welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPERNVIDIA GeForce RTX 4080 SUPER Q4_K_M 15.1 GB / 16.0 GB 45.5 tok/s Runs welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. ASUS TUF Gaming GeForce RTX 5070 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5070 Ti Q4_K_M 15.1 GB / 16.0 GB 55.4 tok/s Runs welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Founders EditionNVIDIA GeForce RTX 5080 Q4_K_M 15.1 GB / 16.0 GB 59.3 tok/s Runs welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 9070 XT OCAMD Radeon RX 9070 XT Q4_K_M 15.1 GB / 16.0 GB 34.1 tok/s Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. ASUS Dual GeForce RTX 5060 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5060 Ti 16GB Q3_K_M 12.7 GB / 16.0 GB 35.8 tok/s Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?