xGemable 12B coder v1.5 needs about 21.0 GB of memory at Q4_K_M (a 7.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 7.6 GB (Q4_K_M) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
xGemable 12B coder v1.5 – a GGUF model for reliable, executable code generation
xGemable 12B coder v1.5 is a GGUF quantized version of google/gemma-4-12B-it, distilled from Anthropic Claude with execution‑verified distillation. It supports coding, reasoning, and tool use, with a 1M token context window. The model is licensed under Apache‑2.0.
Good at
- Executable code generation
- Multi‑language support (Python, C#, Java, Go, JavaScript, Rust)
- Agentic coding with tool use
Limits
- No vision or audio support
- Requires at least 16 GB RAM for GGUF inference
- Large context may need high VRAM
Best for
- Implementing functions from docstrings
- Cross‑file reasoning in medium‑sized repos
- Private on‑premise deployment
Who it’s for. Engineers needing a local, private code assistant that produces compilable, test‑passing code. The model is ideal for developers who prefer a lightweight, open‑source solution over larger, generic instruction models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.6 GB | 21.0 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 16 GB RAM, Q4_K_M (7.63 GB file, 21 GB VRAM at 8 k context) is suitable. If more VRAM is available, Q5_K_M (8.55 GB file, 21.9 GB VRAM) offers higher quality. Q6_K and Q8_0 provide further quality gains but require 23.2 GB and 26.1 GB VRAM respectively.
What GPU do you need for xGemable 12B coder v1.5?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which xGemable 12B coder v1.5 quant should you choose?
Q4_K_M is the usual starting point for xGemable 12B coder v1.5: it balances file size and quality well. Here it is a 7.6 GB file.
The Q8_0 file is 12.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about xGemable 12B coder v1.5
How much VRAM does xGemable 12B coder v1.5 need?
About 21.0 GB at Q4_K_M with an 8K context window. That is the 7.6 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 xGemable 12B coder v1.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of xGemable 12B coder v1.5 GGUF?
It depends on the quant: Q4_K_M is 7.6 GB, Q5_K_M is 8.5 GB, Q6_K is 9.8 GB, Q8_0 is 12.7 GB.
What context length does xGemable 12B coder v1.5 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download xGemable 12B coder v1.5 GGUF?
The files are on Hugging Face in the xCloudinfo/xGemable-12B-coder-v1.5-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 xGemable 12B coder v1.5 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 xGemable 12B coder v1.5 on 8 GB VRAM?
No. The smallest quant requires 21 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support image or audio input?
No. The model is a text‑only coder and does not include vision or audio capabilities.
What license does the model use?
Apache‑2.0, allowing free use and modification for commercial and non‑commercial purposes.