wolfram_miquliz-120b-v2.0-GGUF needs about 40.6 GB of memory at IQ2_XS (a 35.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 25.2 GB (IQ1_S) to 49.0 GB (IQ3_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 18.8 GB.
120B llama‑style model with multiple GGUF quantizations
wolfram_miquliz-120b-v2.0-GGUF is a 120B parameter model based on the Miqu family. It supports a 32768 token context window and is available in several quantized GGUF formats. The model was quantized by Wolfram and builds on the miqu-1-70b-sf parent.
Good at
- Large context handling
- High‑parameter inference
- Multiple quant options
Limits
- No license specified
- No vision support
- Large VRAM requirement for full precision
Best for
- Research prototypes
- High‑capacity text generation
- Benchmarking
Who it’s for. Developers and researchers needing a large llama‑style model with flexible quantization. The model is suitable for environments where memory can be allocated for high‑parameter inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 25.2 GB | 30.4 GB | Too big | Get file → | |
| IQ2_XXS | 31.8 GB | 37.0 GB | Too big | Get file → | |
| IQ2_XS | 35.4 GB | 40.6 GB | Too big | Get file → | |
| Q2_K | 44.2 GB | 49.4 GB | Too big | Get file → | |
| IQ3_XXS | 46.2 GB | 51.3 GB | Too big | Get file → | |
| IQ3_XXS | 49.0 GB | 54.2 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_S (file size 25.22 GB, estimated 30.4 GB at 8k context). For 12‑GB VRAM use IQ2_XXS (31.8 GB, 37 GB). For 16‑GB VRAM use IQ2_XS (35.38 GB, 40.6 GB). Larger VRAM allows Q2_K or IQ3_XXS variants.
What GPU do you need for wolfram_miquliz-120b-v2.0-GGUF?
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 IQ1_S (25.2 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_XS (35.4 GB file, about 40.6 GB in use).
Which wolfram_miquliz-120b-v2.0-GGUF quant should you choose?
IQ2_XS (35.4 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 25.2 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 wolfram_miquliz-120b-v2.0-GGUF
How much VRAM does wolfram_miquliz-120b-v2.0-GGUF need?
About 40.6 GB at IQ2_XS with an 8K context window. That is the 35.4 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 wolfram_miquliz-120b-v2.0-GGUF on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 30.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of wolfram_miquliz-120b-v2.0-GGUF GGUF?
It depends on the quant: IQ1_S is 25.2 GB, IQ2_XXS is 31.8 GB, IQ2_XS is 35.4 GB, Q2_K is 44.2 GB, IQ3_XXS is 46.2 GB, IQ3_XXS is 49.0 GB.
What context length does wolfram_miquliz-120b-v2.0-GGUF support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.7 GB at 8K and 18.8 GB at 32K.
Where can I download wolfram_miquliz-120b-v2.0-GGUF GGUF?
The files are on Hugging Face in the wolfram/miquliz-120b-v2.0-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 this model on 8 GB VRAM?
The smallest quant, IQ1_S, requires about 30.4 GB of VRAM at 8k context, so 8 GB is insufficient.
What is the context length of this model?
The model supports 32768 tokens of context.
Is there a license for this model?
No license information is provided in the supplied facts.