LLMs · xAI

Grok-1 (314B)

Name: Grok-1 (314B)
Author: xAI

Parameters: 314B (86.0B active)
Architecture: Mixture of experts
Max context: 8K tokens
License: apache-2.0
Released: 2024-03

How to run it

Quantized files · GGUF

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

huggingface.co/Arki05/Grok-1-GGUF (opens in a new tab)

ollama run hf.co/Arki05/Grok-1-GGUF

Original weights · Hugging Face

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

huggingface.co/xai-org/grok-1 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/xai-org/grok-1 (opens in a new tab)

git clone https://github.com/xai-org/grok-1

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

Apps that run Grok-1 (314B)

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

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	GGUF from Hugging Face	macOSWindowsLinux	llama.cpp, MLX	`ollama run hf.co/Arki05/Grok-1-GGUF:Q4_K_M`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf Arki05/Grok-1-GGUF:Q4_K_M`
Jan	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve xai-org/grok-1`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path xai-org/grok-1`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/Arki05/Grok-1-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull Arki05/Grok-1-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	Download
`Q2_K`	Low	126 GB	128 GB	GGUF · folder (opens in a new tab)
`Q3_K_M`	Low	154 GB	157 GB	GGUF · folder (opens in a new tab)
`Q4_K_M`	Good	192 GB	194 GB	GGUF files (opens in a new tab)
`Q5_K_M`	High	223 GB	226 GB	GGUF files (opens in a new tab)
`Q6_K`	High	257 GB	260 GB	GGUF · folder (opens in a new tab)
`Q8_0`	Very high	333 GB	336 GB	GGUF · folder (opens in a new tab)
`F16`	Full	628 GB	631 GB	Original weights (opens in a new tab)

Best hardware for Grok-1 (314B)

Quality	Hardware	Quant	Memory	Speed	Runs
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`Q3_K_M`	172 GB / 192 GB	12.5 tok/s	Runs welltight fit
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`Q2_K`	140 GB / 144 GB	15.4 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 63/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`Q3_K_M`	187 GB / 384 GB	12.5 tok/s	Runs well
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.	AMD Instinct MI350X	`Q5_K_M`	240 GB / 288 GB	63.2 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 76/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI325X	`Q4_K_M`	207 GB / 256 GB	59.1 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 76/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip	`Q4_K_M`	207 GB / 252 GB	75.6 tok/s	Runs great
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI300X	`Q3_K_M`	166 GB / 192 GB	66.2 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 72/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA B200	`Q3_K_M`	166 GB / 180 GB	99.9 tok/s	Runs welltight fit
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H200 141GB SXM	`Q2_K`	135 GB / 141 GB	83.2 tok/s	Runs welltight fit
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H200 NVL	`Q2_K`	135 GB / 141 GB	83.2 tok/s	Runs welltight fit

Check it on your own hardware

Run it on a cluster

Devices that can’t run Grok-1 (314B) 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.