Grok-1 (base)
By xAI · United States
Updated 2026-07-13
Overview
xAI's first open-weight release: a 314B MoE with about 86B active parameters under Apache 2.0. Base model only — no official instruction tuning shipped.
When to pick this model
- Research into large-scale MoE architectures
- Custom fine-tuning projects with significant GPU budget
- Historical reference for xAI's open-weight lineage
- Apache-licensed base for downstream instruct training
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 188 GB |
| Q5_K_M | 225 GB |
| Q8_0 | 335 GB |
| FP16 (no quantization) | 630 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Grok-1 (base) is server-class even at Q4_K_M (188 GB). Stepping up to Q8_0 nearly doubles the footprint to 335 GB, and unquantized FP16 weights take 630 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Grok-1 (base) needs roughly 240 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 0.5 tokens/sec on entry-level GPUs, on the order of 2 tokens/sec on a mid-range card, and up to 8 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Grok-1 (base) to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Grok-1 (base) |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 188 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 188 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 188 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Does not fit — needs 188 GB at Q4_K_M |
| 32 GB | RTX 5090 | Does not fit — needs 188 GB at Q4_K_M |
Which GPU should you buy to run Grok-1 (base)?
To run Grok-1 (base) locally at Q4, you need ~188 GB of VRAM. The best value for this is a Apple Mac Studio (64+ GB unified memory).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- First open-weight model from xAI
- Apache 2.0 with full commercial freedom
- Efficient MoE design with top-2 routing across 8 experts
- Useful base for community fine-tunes
Limitations
- Around 188 GB VRAM at Q4
- Raw base weights — no official instruct variant
- Comprehensively outpaced by Grok 2 and beyond
- Limited community fine-tunes vs. Llama or Qwen
Typical workloads
In our catalog grid, Grok-1 (base) is filed under Open xAI Reference, Research — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: everyday chat, drafting and summarization.
Note the 8k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: MoE · 314B total / 86B active · 8 experts, 2 active · xAI
Training: xAI — first xAI open-source model. Raw weights released without official fine-tuning.
A landmark open release that's now mostly a research artifact — pick a modern MoE for any real workload.
Quick start
# Non disponible via Ollama — poids HuggingFace uniquementOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Grok-1 (base) need?
At the recommended Q4_K_M quantization, Grok-1 (base) needs about 188 GB of VRAM. Q8_0 takes 335 GB, and unquantized FP16 weights take 630 GB.
Can Grok-1 (base) run without a GPU?
Yes — with roughly 240 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Grok-1 (base) support?
Grok-1 (base) supports a 8k-token context window (8,192 tokens).
Can I use Grok-1 (base) commercially?
Yes. Grok-1 (base) is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Grok-1 (base) on consumer hardware?
Our compatibility engine estimates on the order of 2 tokens/sec on a mid-range GPU and up to 8 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Grok-1 (base) should I download first?
Start with Q4_K_M (188 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It does not fit a single 24 GB consumer card — plan for multi-GPU or server hardware.