Mellum 4b Sft Rust needs about 6.1 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 3.5 GB (Q6_K).
Mellum 4b Sft Rust – a Rust‑focused LLaMA‑style LLM
Mellum 4b Sft Rust is a 4.02 billion‑parameter LLaMA model fine‑tuned for Rust code Fill‑in‑the‑Middle tasks. It is built on JetBrains Mellum‑4b‑base and trained on ~57,000 Rust FIM examples. The model is available in GGUF format for CPU inference.
Good at
- Rust code completion
- Fill‑in‑the‑Middle tasks
- IDE integration
Limits
- No vision support
- Requires 8 k context for memory estimates
- Apache‑2.0 license
Best for
- Rust IDE assistants
- Code snippet completion
- Local Rust development
Who it’s for. Developers working with Rust who need an LLM that understands Rust syntax and can be integrated into IDEs such as Continue.dev. The model is suitable for both cloud and local deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.5 GB | Fits | Get file → | |
| IQ1_S | 1.3 GB | 4.8 GB | Fits | Get file → | |
| IQ1_M | 1.4 GB | 4.9 GB | Fits | Get file → | |
| IQ2_XXS | 1.4 GB | 5.0 GB | Fits | Get file → | |
| IQ2_XS | 1.5 GB | 5.0 GB | Fits | Get file → | |
| IQ2_S | 1.6 GB | 5.1 GB | Fits | Get file → | |
| Q2_K_S | 1.7 GB | 5.2 GB | Fits | Get file → | |
| IQ2_M | 1.7 GB | 5.2 GB | Fits | Get file → | |
| Q2_K | 1.7 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 5.4 GB | Fits | Get file → | |
| IQ3_S | 2.0 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_S | 2.0 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 5.8 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 2.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 2.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 6.0 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 6.1 GB | Fits | Get file → | |
| Q5_K_S | 2.9 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_M | 3.0 GB | 6.5 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (file size 2.61 GB, estimated 6.1 GB memory). With 6 GB VRAM Q3_K_M (2.12 GB, 5.6 GB memory) is a good compromise. If memory is limited, IQ1_S (1.31 GB, 4.8 GB memory) offers the smallest footprint.
What GPU do you need for Mellum 4b Sft Rust?
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 the main file (0.0 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_S (2.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 7.0 GB in use).
Which Mellum 4b Sft Rust quant should you choose?
Q4_K_M is the usual starting point for Mellum 4b Sft Rust: it balances file size and quality well. Here it is a 2.6 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 Mellum 4b Sft Rust
How much VRAM does Mellum 4b Sft Rust need?
About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.6 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 Mellum 4b Sft Rust on an 8 GB GPU?
Yes, with Q6_K: the 3.5 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mellum 4b Sft Rust GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.3 GB, IQ1_M is 1.4 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB and 19 more.
What context length does Mellum 4b Sft Rust support?
The GGUF header lists a trained context length of 8,200 tokens (8K). The KV cache grows with the context you use: about 3.0 GB at 8K and 3.0 GB at 8K.
Where can I download Mellum 4b Sft Rust GGUF?
The files are on Hugging Face in the mradermacher/Mellum-4b-sft-rust-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 Mellum 4b Sft Rust 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 Mellum 4b Sft Rust on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 6.1 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.