Razorback 12B v0.2 needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 3.0 GB (IQ1_S) to 10.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Razorback 12B v0.2 – a 12.2B llama model with vision and tool use
Razorback 12B v0.2 is a 12.2B parameter llama model that supports vision and tool usage. It merges Pixtral 12B and Mistral Nemo to provide stable visual understanding and engaging text generation. The model is available in multiple GGUF quantizations.
Good at
- Vision input handling
- Tool invocation
- Long‑context generation
Limits
- No chatml support
- Requires 8k context for estimates
- License is other
Best for
- Image‑guided text generation
- Automated tool workflows
- Research on vision‑LLMs
Who it’s for. Developers and researchers who need a vision‑enabled llama model with tool‑use capabilities. The model is suitable for applications that require both visual understanding and text generation within a single inference pipeline.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.0 GB | 4.8 GB | Fits | Get file → | |
| IQ1_M | 3.2 GB | 5.1 GB | Fits | Get file → | |
| IQ2_XXS | 3.6 GB | 5.4 GB | Fits | Get file → | |
| IQ2_XS | 3.9 GB | 5.8 GB | Fits | Get file → | |
| IQ2_S | 4.1 GB | 6.0 GB | Fits | Get file → | |
| IQ2_M | 4.4 GB | 6.3 GB | Fits | Get file → | |
| Q2_K_S | 4.5 GB | 6.3 GB | Fits | Get file → | |
| Q2_K | 4.8 GB | 6.6 GB | Fits | Get file → | |
| IQ3_XXS | 4.9 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 7.1 GB | Fits | Get file → | |
| Q3_K_S | 5.5 GB | 7.4 GB | Tight | Get file → | |
| IQ3_S | 5.6 GB | 7.4 GB | Tight | Get file → | |
| IQ3_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_M | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_L | 6.6 GB | 8.4 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q4_0 | 7.1 GB | 8.9 GB | Too big | Get file → | |
| IQ4_NL | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_S | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_1 | 7.8 GB | 9.6 GB | Too big | Get file → | |
| Q5_K_S | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3 GB) or IQ1_M (3.22 GB). For 12 GB VRAM, IQ2_M (4.44 GB) or Q2_K (4.79 GB) are good choices. For 16 GB VRAM, Q4_K_M (7.48 GB) or Q5_K_M (8.73 GB) provide higher quality while staying within memory limits. Estimates are approximate.
What GPU do you need for Razorback 12B v0.2?
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: the best quant that fits is IQ2_S (4.1 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
Which Razorback 12B v0.2 quant should you choose?
Q4_K_M is the usual starting point for Razorback 12B v0.2: it balances file size and quality well. Here it is a 7.5 GB file.
If memory is tight, the smallest file is IQ1_S at 3.0 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 Razorback 12B v0.2
How much VRAM does Razorback 12B v0.2 need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Razorback 12B v0.2 on an 8 GB GPU?
Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Razorback 12B v0.2 GGUF?
It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB, IQ2_M is 4.4 GB and 18 more.
What context length does Razorback 12B v0.2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Razorback 12B v0.2 GGUF?
The files are on Hugging Face in the mradermacher/Razorback-12B-v0.2-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 Razorback 12B v0.2 use?
Hugging Face lists the license as other. 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 Razorback 12B v0.2 on 8 GB VRAM?
Yes, use the IQ1_S or IQ1_M quantization. They require about 4.8–5.1 GB of VRAM at 8k context.
Does this model support vision?
Yes, it includes vision capabilities and mmproj files are available in the static repository.
Is chatml supported?
No, the model uses a Mistral chat template and does not support chatml yet.