NeoHorse 1 9B Math SFT needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
NeoHorse 1 9B Math SFT – fine‑tuned for math reasoning and Japanese code review
NeoHorse 1 9B Math SFT is a 9‑billion‑parameter Qwen3.5‑based model fine‑tuned with three LoRA stages. It excels at math problem solving and Japanese code explanation. The model is released under Apache‑2.0 and supports reasoning with a 262,144‑token context window.
Good at
- Math reasoning with short proofs
- Japanese code review and repair
- Long‑form reasoning up to 262,144 tokens
Limits
- Large VRAM requirement for higher‑quality quants
- No vision or multimodal support
- Requires 8‑k context for memory estimates
Best for
- Solving AIME‑style math problems
- Reviewing and explaining Japanese code
- Generating detailed reasoning chains
Who it’s for. Developers and researchers needing a math‑focused LLM with Japanese code support. The model is suitable for academic work, coding assistance, and research on reasoning chains.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 2.7 GB | 4.3 GB | Fits | Get file → | |
| IQ1_M | 2.9 GB | 4.5 GB | Fits | Get file → | |
| IQ2_XXS | 3.1 GB | 4.7 GB | Fits | Get file → | |
| IQ2_XS | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ2_S | 3.4 GB | 5.0 GB | Fits | Get file → | |
| IQ2_M | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q2_K_S | 3.7 GB | 5.3 GB | Fits | Get file → | |
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XXS | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ3_XS | 4.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| IQ3_S | 4.4 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| IQ4_NL | 5.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q4_1 | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.74 GB, 4.3 GB memory) or Q2_K (3.83 GB, 5.4 GB memory). With 12 GB VRAM, Q3_K_M (4.62 GB, 6.2 GB memory) or Q4_K_M (5.63 GB, 7.2 GB memory) provide a good balance of size and performance. Larger quants such as Q5_K_M (6.47 GB, 8 GB memory) require 16 GB or more.
What GPU do you need for NeoHorse 1 9B Math SFT?
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_M (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.4 GB file, about 8.9 GB in use).
Which NeoHorse 1 9B Math SFT quant should you choose?
Q4_K_M is the usual starting point for NeoHorse 1 9B Math SFT: it balances file size and quality well. Here it is a 5.6 GB file.
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 NeoHorse 1 9B Math SFT
How much VRAM does NeoHorse 1 9B Math SFT need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 NeoHorse 1 9B Math SFT on an 8 GB GPU?
Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NeoHorse 1 9B Math SFT GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.7 GB, IQ1_M is 2.9 GB, IQ2_XXS is 3.1 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.4 GB and 19 more.
What context length does NeoHorse 1 9B Math SFT 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 4.3 GB at 32K.
Where can I download NeoHorse 1 9B Math SFT GGUF?
The files are on Hugging Face in the mradermacher/NeoHorse-1-9B-Math-SFT-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 NeoHorse 1 9B Math SFT 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 NeoHorse 1 9B Math SFT on 8 GB VRAM?
Use the IQ1_S or Q2_K quant; they fit within 8 GB VRAM and use about 4–5 GB of memory at 8 k context.
Does the model support image input?
No, NeoHorse 1 9B Math SFT is a text‑only model with no vision capabilities.
What license applies to this model?
The model is released under Apache License 2.0, compatible with open‑source projects.