GLM 4.5 DRAFT 0.6B v3.0 needs about 1.1 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
GLM 4.5 DRAFT 0.6B v3.0 – a 0.6B parameter draft model for GLM-4.5 family
GLM 4.5 DRAFT 0.6B v3.0 is a 0.6B parameter draft model built on Qwen2 architecture. It supports a context length of 32768 tokens and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations for llama.cpp.
Good at
- Draft decoding with GLM-4.5
- Low‑memory inference
- Extending context to 32k tokens
Limits
- No vision support
- Requires static‑YaRN scaling for longer contexts
- Only available in GGUF format
Best for
- Fast prototype testing
- Low‑budget local inference
- Research on draft models
Who it’s for. Developers and researchers who need a lightweight draft model for the GLM‑4.5 ecosystem. The model is suitable for local deployment with llama.cpp and for experimentation with context scaling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ1_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ1_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XXS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ4_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ4_NL | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_1 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_1 (0.46 GB file, 1.1 GB memory) or Q4_K_S (0.48 GB, 1.1 GB). For 4 GB VRAM, choose Q4_0 (0.43 GB, 1 GB) or Q3_K_S (0.42 GB, 1 GB). Larger VRAM allows Q5_K_M (0.52 GB, 1.1 GB) or Q6_K (0.65 GB, 1.3 GB). Estimates are approximate.
What GPU do you need for GLM 4.5 DRAFT 0.6B v3.0?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q6_K (0.7 GB file, about 1.3 GB in use).
Which GLM 4.5 DRAFT 0.6B v3.0 quant should you choose?
Q4_K_M is the usual starting point for GLM 4.5 DRAFT 0.6B v3.0: it balances file size and quality well. Here it is a 0.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 4.5 DRAFT 0.6B v3.0
How much VRAM does GLM 4.5 DRAFT 0.6B v3.0 need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run GLM 4.5 DRAFT 0.6B v3.0 on an 8 GB GPU?
Yes, with Q6_K: the 0.7 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4.5 DRAFT 0.6B v3.0 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.
What context length does GLM 4.5 DRAFT 0.6B v3.0 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download GLM 4.5 DRAFT 0.6B v3.0 GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.5-DRAFT-0.6B-v3.0-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GLM 4.5 DRAFT 0.6B v3.0 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, using Q4_1 or Q4_K_S quantizations will fit within 8 GB VRAM with an estimated memory usage of 1.1 GB at 8k context.
Does this model support vision tasks?
No, the model has no vision capabilities and is text‑only.
How do I extend the context beyond 32k tokens?
Add a "rope_scaling" section to config.json to enable static‑YaRN scaling for longer contexts.