GLM 4.6 Derestricted v3 — Hardware Requirements & GPU Compatibility
Chat
1.3K downloads
37 likesSpecifications
- Publisher
- ArliAI
- Family
- GLM
- Parameters
- 356.8B
- Architecture
- Glm4MoeForCausalLM
- Context Length
- 202,752 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-12-10
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.6 Derestricted v3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 714.2 GB | 745.7 GB | 713.57 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run GLM 4.6 Derestricted v3?
BF16 · 714.2 GBGLM 4.6 Derestricted v3 (BF16) requires 714.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 929+ GB is recommended. Using the full 203K context window can add up to 31.5 GB, bringing total usage to 745.7 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Related Models
Frequently Asked Questions
- How much VRAM does GLM 4.6 Derestricted v3 need?
GLM 4.6 Derestricted v3 requires 714.2 GB of VRAM at BF16. Full 203K context adds up to 31.5 GB (745.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 356.8B × 16 bits ÷ 8 = 713.6 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 32.1 GB (at full 203K context)
VRAM usage by quantization
BF16714.2 GBBF16 + full context745.7 GB- Can NVIDIA GeForce RTX 5090 run GLM 4.6 Derestricted v3?
No — GLM 4.6 Derestricted v3 requires at least 714.2 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run GLM 4.6 Derestricted v3 on a Mac?
GLM 4.6 Derestricted v3 requires at least 714.2 GB at BF16, 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 GLM 4.6 Derestricted v3 locally?
Yes — GLM 4.6 Derestricted v3 can run locally on consumer hardware. At BF16 quantization it needs 714.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of GLM 4.6 Derestricted v3?
At BF16, the download is about 713.57 GB.
- Which GPUs can run GLM 4.6 Derestricted v3?
No single consumer GPU has enough VRAM to run GLM 4.6 Derestricted v3 at BF16 (714.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run GLM 4.6 Derestricted v3?
GLM 4.6 Derestricted v3 requires at least 714.2 GB at BF16, which exceeds the unified memory of most consumer devices. A high-memory Mac Studio, Mac Pro, or multi-GPU desktop setup is recommended.