Llemma_7B needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K).
Llemma 7B – a 6.74B‑parameter math‑focused language model
Llemma 7B is a 6.74B‑parameter language model built on the llama architecture. It is trained on the Proof‑Pile‑2 for 200B tokens and excels at chain‑of‑thought mathematical reasoning and tool use. The model supports a 4096‑token context window.
Good at
- Chain‑of‑thought math reasoning
- Computational tool use
- Formal theorem proving
Limits
- No vision support
- License is llama2
- Requires 8‑k context for memory estimates
Best for
- Math tutoring
- Code‑based problem solving
- Academic research in mathematics
Who it’s for. Developers and researchers needing a specialized mathematical language model. The model is suitable for applications that require precise reasoning and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.5 GB | 4.2 GB | Fits | Get file → | |
| IQ1_M | 1.7 GB | 4.3 GB | Fits | Get file → | |
| IQ2_XXS | 1.9 GB | 4.5 GB | Fits | Get file → | |
| IQ2_XS | 2.0 GB | 4.7 GB | Fits | Get file → | |
| IQ2_S | 2.2 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_S | 2.3 GB | 5.0 GB | Fits | Get file → | |
| IQ2_M | 2.4 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 2.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 2.6 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XS | 2.8 GB | 5.4 GB | Fits | Get file → | |
| IQ3_S | 2.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 5.6 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 3.3 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_L | 3.6 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 3.6 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 3.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 3.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 6.7 GB | Fits | Get file → | |
| Q4_1 | 4.2 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_S | 4.7 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_M | 4.8 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 5.5 GB | 8.2 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (1.53 GB, 6.3 GB memory) or IQ1_M (1.65 GB, 6.4 GB memory). If more VRAM is available, Q4_K_M (4.08 GB, 8.9 GB memory) offers higher quality. Memory estimates are approximate.
What GPU do you need for Llemma_7B?
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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).
Which Llemma_7B quant should you choose?
Q4_K_M is the usual starting point for Llemma_7B: it balances file size and quality well. Here it is a 4.1 GB file.
If memory is tight, the smallest file is IQ1_S at 1.5 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 Llemma_7B
How much VRAM does Llemma_7B need?
About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Llemma_7B on an 8 GB GPU?
Yes, with IQ3_M: the 3.1 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 Llemma_7B GGUF?
It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, Q2_K_S is 2.3 GB and 18 more.
What context length does Llemma_7B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download Llemma_7B GGUF?
The files are on Hugging Face in the mradermacher/llemma_7b-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 Llemma_7B use?
Hugging Face lists the license as llama2. 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 Llemma 7B on 8 GB VRAM?
Yes, the IQ1_S or IQ1_M quantizations fit within 8 GB VRAM, using about 6.3–6.4 GB of memory at 8‑k context.
Does Llemma 7B support vision tasks?
No, the model does not include vision capabilities.