LLMs ·

Qwen3.8 Max (2.4T-A95B)

Parameters
2,446B (95.0B active)
Architecture
Mixture of experts
Max context
256K tokens
License
qwen3.8-max
Released
2026-08

How to run it

Quantized files · GGUF

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

huggingface.co/unsloth/Qwen3.8-2.4T-A95B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.8-2.4T-A95B-GGUF

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen3.8-2.4T-A95B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba. The weights themselves download from Hugging Face.

github.com/QwenLM/Qwen3.8 (opens in a new tab)

Qwen’s current repo: Qwen3.5 and Qwen3.6 redirect here.

git clone https://github.com/QwenLM/Qwen3.8

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

Apps that run Qwen3.8 Max (2.4T-A95B)

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)

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Windows PC, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

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

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Linux server, 80 GB+ GPUs

LM Studio

Point-and-click: search, download and chat in one window.

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 GGUF from Hugging Face macOSWindowsLinux llama.cpp, MLX 
ollama run hf.co/unsloth/Qwen3.8-2.4T-A95B-GGUF:Q4_K_M
llama.cpp CLI + API GGUF macOSWindowsLinux llama.cpp 
llama-server -hf unsloth/Qwen3.8-2.4T-A95B-GGUF:Q4_K_M
Jan Desktop app GGUF macOSWindowsLinux llama.cpp, MLX Open in Jan
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve Qwen/Qwen3.8-2.4T-A95B
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path Qwen/Qwen3.8-2.4T-A95B
Docker Model Runner CLI + API GGUF macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/unsloth/Qwen3.8-2.4T-A95B-GGUF:Q4_K_M
Lemonade Desktop app GGUF macOSWindowsLinux llama.cpp, ONNX Runtime GenAI 
lemonade pull unsloth/Qwen3.8-2.4T-A95B-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
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.

KV cache: hybrid: only the full-attention layers (1 in 4) keep a KV cache; the rest use linear attention.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 978 GB 980 GB 982 GB GGUF (IQ2_XXS) · folder (opens in a new tab)
Q3_K_M Low 1,199 GB 1,200 GB 1,202 GB GGUF (IQ3_XXS) · folder (opens in a new tab)
Q4_K_M Good 1,492 GB 1,494 GB 1,496 GB GGUF files (opens in a new tab)
Q5_K_M High 1,737 GB 1,738 GB 1,740 GB GGUF files (opens in a new tab)
Q6_K High 2,006 GB 2,007 GB 2,010 GB GGUF files (opens in a new tab)
Q8_0 Very high 2,593 GB 2,594 GB 2,597 GB GGUF · folder (opens in a new tab)
F16 Full 4,892 GB 4,894 GB 4,896 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Qwen3.8 Max (2.4T-A95B)

None. No single GPU or device in our catalog runs this model on its own; it needs several GPUs working together.

Check it on your own hardware

Run it on a cluster

Devices that can’t run Qwen3.8 Max (2.4T-A95B) alone can run it together. These example clusters do:

Try it with your own devices

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?