SpellBlade needs about 45.4 GB of memory at Q4_K_M (a 42.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 26.3 GB (Q2_K) to 48.3 GB (Q5_K_S).
SpellBlade – a 69‑billion‑parameter Llama‑based chat model
SpellBlade is a 69‑billion‑parameter Llama model fine‑tuned for chat and general tasks. It supports a 4096‑token context window and is released under the apache‑2.0 license.
Good at
- Chatting with structured prompts
- Technical question answering
- General-purpose text generation
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No mixture‑of‑experts
Best for
- Developers building chatbots
- Researchers testing large‑scale LLMs
- Fine‑tuning for domain‑specific tasks
Who it’s for. This model is suitable for developers and researchers who need a large Llama‑based model for conversational AI and general text generation. It is a legacy reference model; newer Llama 3 variants are recommended for most use cases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 26.3 GB | 28.1 GB | Too big | Get file → | |
| IQ3_XS | 29.0 GB | 30.8 GB | Too big | Get file → | |
| IQ3_S | 30.8 GB | 32.6 GB | Too big | Get file → | |
| Q3_K_S | 30.8 GB | 32.6 GB | Too big | Get file → | |
| IQ3_M | 31.8 GB | 33.6 GB | Too big | Get file → | |
| Q3_K_M | 34.1 GB | 36.0 GB | Too big | Get file → | |
| Q3_K_L | 37.0 GB | 38.8 GB | Too big | Get file → | |
| IQ4_XS | 38.0 GB | 39.9 GB | Too big | Get file → | |
| Q4_K_S | 40.1 GB | 41.9 GB | Too big | Get file → | |
| Q4_K_M | 42.3 GB | 44.1 GB | Too big | Get file → | |
| Q5_K_S | 48.3 GB | 50.1 GB | Too big | Get file → |
For 8‑GB VRAM use the Q2_K quant (26.3 GB file, ~29.5 GB memory at 8‑k context). With 12‑GB VRAM the Q3_K_S or IQ3_S quants (30.75 GB file, ~33.9 GB memory) are suitable. For 24‑GB VRAM the Q4_K_M quant (42.26 GB file, ~45.4 GB memory) fits well.
What GPU do you need for SpellBlade?
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q2_K (26.3 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (42.3 GB file, about 45.4 GB in use).
Which SpellBlade quant should you choose?
Q4_K_M is the usual starting point for SpellBlade: it balances file size and quality well. Here it is a 42.3 GB file.
If memory is tight, the smallest file is Q2_K at 26.3 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 SpellBlade
How much VRAM does SpellBlade need?
About 45.4 GB at Q4_K_M with an 8K context window. That is the 42.3 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 SpellBlade on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SpellBlade GGUF?
It depends on the quant: Q2_K is 26.3 GB, IQ3_XS is 29.0 GB, IQ3_S is 30.8 GB, Q3_K_S is 30.8 GB, IQ3_M is 31.8 GB, Q3_K_M is 34.1 GB and 5 more.
What context length does SpellBlade support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download SpellBlade GGUF?
The files are on Hugging Face in the mradermacher/SpellBlade-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 SpellBlade 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 SpellBlade on 8 GB VRAM?
Yes, the Q2_K quant requires about 29.5 GB memory at 8‑k context, which is within 8‑GB VRAM when using 8‑k context and efficient memory management.
Does SpellBlade support vision tasks?
No, SpellBlade is a text‑only model and does not support vision inputs.
What license applies to SpellBlade?
SpellBlade is released under the apache‑2.0 license, allowing free use and modification.