Strand-Rust-Coder-14B-v1 needs about 11.4 GB of memory at Q4_K_M (a 9.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 40 quants, from 0.0 GB to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Strand‑Rust‑Coder‑14B‑v1 – a Rust‑specialized code LLM
Strand‑Rust‑Coder‑14B‑v1 is a 14.8‑billion‑parameter Qwen model fine‑tuned for Rust programming. It is trained on 191,008 peer‑validated synthetic examples and achieves 43–48% accuracy on Rust‑specific benchmarks. The model supports a full 131,072‑token context length.
Good at
- Rust code generation
- Rust code reasoning
- Rust code fixing
Limits
- No vision support
- Requires 8,192‑token context for full performance
- License is apache‑2.0
Best for
- Rust code autocompletion
- Rust unit test generation
- Rust code review
Who it’s for. Developers building or maintaining Rust codebases who need a specialized LLM for code generation and debugging. The model is suitable for teams looking for open‑source alternatives to proprietary code assistants.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ1_S | 5.6 GB | 7.7 GB | Tight | Get file → | |
| IQ2_XXS | 5.6 GB | 7.7 GB | Tight | Get file → | |
| Q2_K_S | 6.5 GB | 8.6 GB | Too big | Get file → | |
| IQ3_XXS | 6.6 GB | 8.7 GB | Too big | Get file → | |
| Q2_K_M | 6.7 GB | 8.8 GB | Too big | Get file → | |
| IQ1_M | 6.9 GB | 9.0 GB | Too big | Get file → | |
| IQ2_XS | 6.9 GB | 9.0 GB | Too big | Get file → | |
| IQ3_XS | 6.9 GB | 9.1 GB | Too big | Get file → | |
| IQ2_S | 7.1 GB | 9.2 GB | Too big | Get file → | |
| Q2_K_L | 7.1 GB | 9.2 GB | Too big | Get file → | |
| IQ2_M | 7.1 GB | 9.2 GB | Too big | Get file → | |
| IQ3_M | 7.3 GB | 9.4 GB | Too big | Get file → | |
| IQ3_S | 7.3 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_S | 8.0 GB | 10.1 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_M | 8.2 GB | 10.3 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 10.4 GB | Too big | Get file → | |
| IQ4_NL | 8.5 GB | 10.7 GB | Too big | Get file → | |
| Q3_K_L | 8.6 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_S | 9.0 GB | 11.1 GB | Too big | Get file → | |
| Q4_0 | 9.1 GB | 11.2 GB | Too big | Get file → | |
| Q4_1 | 9.2 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_M | 9.3 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_L | 9.7 GB | 11.8 GB | Too big | Get file → | |
| Q4_1 | 9.9 GB | 12.0 GB | Too big | Get file → | |
| Q5_0 | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_S | 10.7 GB | 12.8 GB | Too big | Get file → | |
| Q5_0 | 10.7 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_M | 10.8 GB | 12.9 GB | Too big | Get file → | |
| Q5_1 | 11.1 GB | 13.2 GB | Too big | Get file → | |
| Q5_K_L | 11.2 GB | 13.3 GB | Too big | Get file → | |
| Q5_1 | 11.6 GB | 13.7 GB | Too big | Get file → | |
| Q6_K_M | 12.1 GB | 14.2 GB | Too big | Get file → | |
| Q6_K_L | 12.5 GB | 14.6 GB | Too big | Get file → | |
| Q8_0 | 15.7 GB | 17.8 GB | Too big | Get file → | |
| BF16 | 21.8 GB | 23.9 GB | Too big | Get file → | |
| F16 | 21.8 GB | 23.9 GB | Too big | Get file → | |
| BF16 | 29.5 GB | 31.7 GB | Too big | Get file → | |
| F16 | 29.5 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K_S (6.53 GB, 8.6 GB memory). For 12 GB VRAM use Q4_K_M (9.3 GB, 11.4 GB memory). For 16 GB VRAM use Q5_K_M (10.84 GB, 12.9 GB memory). Estimates are approximate.
What GPU do you need for Strand-Rust-Coder-14B-v1?
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 2.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_S (5.6 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.9 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_L (12.5 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (21.8 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.7 GB in use).
Which Strand-Rust-Coder-14B-v1 quant should you choose?
Q4_K_M is the usual starting point for Strand-Rust-Coder-14B-v1: it balances file size and quality well. Here it is a 9.3 GB file.
The Q8_0 file is 15.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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 Strand-Rust-Coder-14B-v1
How much VRAM does Strand-Rust-Coder-14B-v1 need?
About 11.4 GB at Q4_K_M with an 8K context window. That is the 9.3 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 Strand-Rust-Coder-14B-v1 on an 8 GB GPU?
Yes, with IQ1_S: the 5.6 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Strand-Rust-Coder-14B-v1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 5.6 GB, IQ2_XXS is 5.6 GB, Q2_K_S is 6.5 GB, IQ3_XXS is 6.6 GB, Q2_K_M is 6.7 GB and 34 more.
What context length does Strand-Rust-Coder-14B-v1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Strand-Rust-Coder-14B-v1 GGUF?
The files are on Hugging Face in the Mungert/Strand-Rust-Coder-14B-v1-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 Strand-Rust-Coder-14B-v1 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 Strand‑Rust‑Coder‑14B‑v1 on 8 GB VRAM?
Yes, using the Q2_K_S quantization which requires about 8.6 GB of VRAM at 8 k context.
Does this model support image input?
No, the model has no vision capabilities.
What is the context length of this model?
The model supports up to 131,072 tokens of context.