Bitnet M7 70m i1 needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.0 GB (IQ1_S) to 0.1 GB (Q6_K).
Bitnet M7 70m i1 – 77.5 M parameter llama model in GGUF format
Bitnet M7 70m i1 is a 77.5 M parameter llama model quantized to 1.5‑bit and higher. It is derived from liminerity/Bitnet-M7-70m and trained on the abideen/cosmopedia‑100k‑pretain dataset. The model is available in multiple quantizations on Hugging Face.
Good at
- Small‑parameter inference
- Fast loading
- Low VRAM usage
Limits
- No vision support
- Context limited to 768 tokens
- License not specified
Best for
- Embedded LLMs
- Edge inference
- Rapid prototyping
Who it’s for. Developers needing a lightweight llama model for local inference. The model is suitable for projects where memory is limited and fast startup is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ1_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_XXS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_S | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ2_M | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q2_K_S | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ3_XXS | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q2_K | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ3_XS | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ3_S | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_S | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ3_M | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_L | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ4_NL | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_1 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S or IQ1_M (0.03 GB file, ~0.7 GB memory). If you have 4 GB VRAM, IQ2_XXS or IQ2_XS (0.03 GB file) are appropriate. For 2 GB VRAM, IQ2_S (0.04 GB file) is the smallest option. All estimates are approximate.
What GPU do you need for Bitnet M7 70m i1?
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 (0.1 GB file, about 0.7 GB in use).
Which Bitnet M7 70m i1 quant should you choose?
Q4_K_M is the usual starting point for Bitnet M7 70m i1: it balances file size and quality well. Here it is a 0.1 GB file.
If memory is tight, the smallest file is IQ1_S at 0.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bitnet M7 70m i1
How much VRAM does Bitnet M7 70m i1 need?
About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Bitnet M7 70m i1 on an 8 GB GPU?
Yes, with Q6_K: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bitnet M7 70m i1 GGUF?
It depends on the quant: IQ1_S is 0.0 GB, IQ1_M is 0.0 GB, IQ2_XXS is 0.0 GB, IQ2_XS is 0.0 GB, IQ2_S is 0.0 GB, IQ2_M is 0.0 GB and 18 more.
What context length does Bitnet M7 70m i1 support?
The GGUF header lists a trained context length of 768 tokens (768). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 768.
Where can I download Bitnet M7 70m i1 GGUF?
The files are on Hugging Face in the mradermacher/Bitnet-M7-70m-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Bitnet M7 70m i1 on 4 GB VRAM?
Yes, using IQ2_XXS or IQ2_XS quantizations, which are 0.03 GB files and use about 0.7 GB memory at 8k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
What context length does it support?
The trained context length is 768 tokens.