Mario Html v2 9B needs about 7.6 GB of memory at Q4_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 23 quants, from 0.0 GB to 18.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Mario Html v2 9B – a 9.2B parameter Qwen‑35 model with reasoning, tools, and vision
Mario Html v2 9B is a 9.2B parameter Qwen‑35 model released under Apache‑2.0. It supports text, image, reasoning, and tool use. The model is available in multiple GGUF quantizations for llama.cpp.
Good at
- Reasoning and chain‑of‑thought
- Tool invocation
- Vision input
Limits
- No speculative decoding
- No built‑in vision support without mmproj
- Requires 262144 context tokens
Best for
- Chat interfaces with reasoning
- Tool‑enabled workflows
- Image‑based question answering
Who it’s for. Developers building chat or web UI applications that need reasoning, tool use, and optional vision. The model is suitable for users who can run llama.cpp and manage GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_M | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q2_K | 3.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XXS | 4.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_S | 4.4 GB | 6.0 GB | Fits | Get file → | |
| IQ3_XS | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.8 GB | 6.4 GB | Fits | Get file → | |
| IQ3_M | 5.0 GB | 6.6 GB | Fits | Get file → | |
| IQ4_XS | 5.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q4_0 | 5.6 GB | 7.2 GB | Tight | Get file → | |
| IQ4_NL | 6.0 GB | 7.6 GB | Tight | Get file → | |
| Q4_K_M | 6.0 GB | 7.6 GB | Tight | Get file → | |
| Q4_1 | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q4_K_L | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_S | 6.7 GB | 8.3 GB | Too big | Get file → | |
| Q5_K_M | 7.0 GB | 8.7 GB | Too big | Get file → | |
| Q6_K_S | 7.7 GB | 9.3 GB | Too big | Get file → | |
| Q6_K | 8.0 GB | 9.6 GB | Too big | Get file → | |
| Q6_K_L | 8.3 GB | 9.9 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 11.4 GB | Too big | Get file → | |
| BF16 | 18.4 GB | 20.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.98 GB) or Q5_K_M (7.04 GB). For 12 GB VRAM, Q6_K (7.99 GB) or Q8_0 (9.8 GB) provide higher quality. The unknown quant is only 0.01 GB but memory usage is not specified.
What GPU do you need for Mario Html v2 9B?
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 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XS (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_L (6.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (18.4 GB file, about 20.0 GB in use).
Which Mario Html v2 9B quant should you choose?
Q4_K_M is the usual starting point for Mario Html v2 9B: it balances file size and quality well. Here it is a 6.0 GB file.
The Q8_0 file is 9.8 GB, about 1.6 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 Mario Html v2 9B
How much VRAM does Mario Html v2 9B need?
About 7.6 GB at Q4_K_M with an 8K context window. That is the 6.0 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 Mario Html v2 9B on an 8 GB GPU?
Yes, with Q4_K_L: the 6.3 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 Mario Html v2 9B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 3.6 GB, Q2_K is 3.7 GB, IQ3_XXS is 4.2 GB, Q3_K_S is 4.4 GB, IQ3_XS is 4.4 GB and 17 more.
What context length does Mario Html v2 9B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download Mario Html v2 9B GGUF?
The files are on Hugging Face in the bartowski/wesjos_mario-html-v2-9B-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 Mario Html v2 9B 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 Mario Html v2 9B on 8 GB VRAM?
Yes, the Q4_K_M quant is 5.98 GB and uses 7.6 GB at 8k context, which fits 8 GB VRAM.
Does the model support vision?
Yes, it supports image input with an mmproj file, but vision is not built‑in without that file.
What license does the model use?
The model is released under the Apache‑2.0 license.