D1 Omni 600M — Hardware Requirements & GPU Compatibility
Vision
d1-omni-600M is Liquid AI's compact decision model for text, images and speech, with 587 million parameters, built on LFM2.5-Encoder-350M. It is given a state as text or JSON, with images or up to 30 seconds of speech, plus a set of named questions, and returns typed answers in one forward pass with zero output tokens, read directly from the model's distribution over the options. Its parameters split into a 381M shared trunk and decision head, a 94M SigLIP2 vision encoder and a 112M audio encoder. It is small enough to run on almost any laptop or edge device. The context length is 16,384 tokens, counting text, image and audio positions together. It is released under the LFM Open License v1.0 (lfm1.0), which is Liquid AI's own license with its own terms rather than a standard open-source license. Published in October 2026, it is the smaller, multimodal sibling of d1-3B.
9.5K downloads
94 likesSpecifications
- Publisher
- Liquid AI
- Parameters
- 587M
- Architecture
- D1OmniModel
- Context Length
- 128,000 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2026-10-05
- License
- Other
Get Started
HuggingFace
Run in cloud
Fits on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~325 tok/s
- generation speed
- Cost per 1M output tokens
- $0.052
- per 1M output tokens
How Much VRAM Does D1 Omni 600M Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 0.6 GB | 4.7 GB | 0.25 GB | 2-bit quantization with K-quant improvements |
| IQ3_M | 3.60 | 0.6 GB | 4.8 GB | 0.26 GB | Importance-weighted 3-bit, medium |
| Q3_K_Mest. | 3.90 | 0.7 GB | 4.8 GB | 0.29 GB | 3-bit medium quantization |
| IQ4_XS | 4.30 | 0.7 GB | 4.8 GB | 0.32 GB | Importance-weighted 4-bit, compact |
| Q4_K_M | 4.80 | 0.7 GB | 4.8 GB | 0.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 0.8 GB | 4.9 GB | 0.42 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 0.8 GB | 5.0 GB | 0.48 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 0.9 GB | 5.1 GB | 0.59 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 1.5 GB | 5.7 GB | 1.17 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 D1 Omni 600M?
Q4_K_M · 0.7 GBD1 Omni 600M (Q4_K_M) requires 0.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 128K context window can add up to 4.1 GB, bringing total usage to 4.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run D1 Omni 600M?
Q4_K_M · 0.7 GB59 devices with unified memory can run D1 Omni 600M, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download D1 Omni 600M
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does D1 Omni 600M need?
D1 Omni 600M requires 0.7 GB of VRAM at Q4_K_M, or 1.5 GB at BF16. Full 128K context adds up to 4.1 GB (4.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 587M × 4.8 bits ÷ 8 = 0.4 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 4.4 GB (at full 128K context)
VRAM usage by quantization
Q4_K_M0.7 GBQ4_K_M + full context4.8 GB- What's the best quantization for D1 Omni 600M?
For D1 Omni 600M, Q4_K_M (0.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.6 GB.
VRAM requirement by quantization
Q2_K0.6 GBQ3_K_M0.7 GBQ4_K_M ★0.7 GBQ5_K_M0.8 GBQ6_K0.8 GBBF161.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run D1 Omni 600M on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 38 other Macs can run D1 Omni 600M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.7 GB of usable unified memory (RAM minus macOS overhead).
- Can I run D1 Omni 600M locally?
Yes — D1 Omni 600M can run locally on consumer hardware. At Q4_K_M quantization it needs 0.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is D1 Omni 600M?
At Q4_K_M, D1 Omni 600M can reach ~6667 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~910 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.72 × 0.65 = ~7222 tok/s
Estimated speed at Q4_K_M (0.7 GB)
~7222 tok/s~910 tok/s~7222 tok/s~6667 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of D1 Omni 600M?
At Q4_K_M, the download is about 0.35 GB. The full-precision BF16 version is 1.17 GB. The smallest option (Q2_K) is 0.25 GB.
- Which GPUs can run D1 Omni 600M?
52 consumer GPUs can run D1 Omni 600M at Q4_K_M (0.7 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run D1 Omni 600M?
59 devices with unified memory can run D1 Omni 600M at Q4_K_M (0.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.