Inkling — Hardware Requirements & GPU Compatibility
VisionChat
Inkling is a 952.4B-parameter open language model from Thinking Machines in the Inkling family. At Q4_K_M it needs about 572.14 GB of VRAM — see which GPUs and Macs can run it below.
13.5K downloads
1.2K likesSpecifications
- Publisher
- Thinking Machines
- Family
- Inkling
- Parameters
- 952.4B
- Architecture
- InklingForConditionalGeneration
- Vocabulary Size
- 201,024
- Release Date
- 2026-07-14
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Inkling Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 405.5 GB | — | 404.76 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 465 GB | — | 464.28 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 572.1 GB | — | 571.43 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 679.3 GB | — | 678.57 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 786.4 GB | — | 785.71 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 953.1 GB | — | 952.38 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 1905.5 GB | — | 1904.76 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Inkling?
Q4_K_M · 572.1 GBInkling (Q4_K_M) requires 572.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 744+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Inkling?
Q4_K_M · 572.1 GB2 devices with unified memory can run Inkling, including NVIDIA DGX H100.
Decent
— Enough memory, may be tightWhere to Download Inkling
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Frequently Asked Questions
- How much VRAM does Inkling need?
Inkling requires 572.1 GB of VRAM at Q4_K_M, or 1905.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 952.4B × 4.8 bits ÷ 8 = 571.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M572.1 GB- Can NVIDIA GeForce RTX 5090 run Inkling?
No — Inkling requires at least 405.5 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Inkling?
For Inkling, Q4_K_M (572.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (679.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 405.5 GB.
VRAM requirement by quantization
Q2_K405.5 GBQ4_K_M ★572.1 GBQ5_K_M679.3 GBQ6_K786.4 GBQ8_0953.1 GBBF161905.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Inkling on a Mac?
Inkling requires at least 405.5 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Inkling locally?
Yes — Inkling can run locally on consumer hardware. At Q4_K_M quantization it needs 572.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of Inkling?
At Q4_K_M, the download is about 571.43 GB. The full-precision BF16 version is 1904.76 GB. The smallest option (Q2_K) is 404.76 GB.
- Which GPUs can run Inkling?
No single consumer GPU has enough VRAM to run Inkling at Q4_K_M (572.1 GB). Multi-GPU or professional hardware is required.
- Which devices can run Inkling?
2 devices with unified memory can run Inkling at Q4_K_M (572.1 GB), including NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.