llama3 42b v0 needs about 28.2 GB of memory at Q4_K_M (a 26.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 14 quants, from 16.3 GB (Q2_K) to 45.9 GB (Q8_0).
Llama 3 42B base model, 43.2B parameters, 8192 context tokens
Llama 3 42B v0 is a pruned base model from Meta’s Llama 3 70B. It contains 43.2B parameters and supports a 8192 token context window. The model is untrained for instruction following and should be used with appropriate prompts.
Good at
- Large context handling
- High parameter count
- Base foundation for further tuning
Limits
- No instruction tuning, random noise with Llama 3 instruction format
- No vision support
- License: llama3
Best for
- Foundation model for custom instruction tuning
- Research on pruning effects
- Benchmarking large language models
Who it’s for. Researchers and developers who need a large, untrained Llama 3 base model for fine‑tuning or experimentation. It is not suitable for out‑of‑the‑box instruction following.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 16.3 GB | 18.4 GB | Too big | Get file → | |
| IQ3_XS | 18.1 GB | 20.2 GB | Too big | Get file → | |
| Q3_K_S | 19.0 GB | 21.1 GB | Too big | Get file → | |
| IQ3_S | 19.0 GB | 21.1 GB | Too big | Get file → | |
| IQ3_M | 19.6 GB | 21.8 GB | Too big | Get file → | |
| Q3_K_M | 21.0 GB | 23.2 GB | Too big | Get file → | |
| Q3_K_L | 22.8 GB | 24.9 GB | Too big | Get file → | |
| IQ4_XS | 23.5 GB | 25.6 GB | Too big | Get file → | |
| Q4_K_S | 24.7 GB | 26.9 GB | Too big | Get file → | |
| Q4_K_M | 26.1 GB | 28.2 GB | Too big | Get file → | |
| Q5_K_S | 29.8 GB | 31.9 GB | Too big | Get file → | |
| Q5_K_M | 30.6 GB | 32.7 GB | Too big | Get file → | |
| Q6_K | 35.4 GB | 37.5 GB | Too big | Get file → | |
| Q8_0 | 45.9 GB | 48.0 GB | Too big | Get file → |
For 8‑GB VRAM, use Q2_K (16.26 GB file, 18.4 GB memory at 8K context). For 16‑GB VRAM, Q4_K_M (26.07 GB file, 28.2 GB memory) is a good balance. For 32‑GB VRAM, Q5_K_M (30.61 GB file, 32.7 GB memory) or Q6_K (35.43 GB file, 37.5 GB memory) are suitable. Memory estimates are approximate.
What GPU do you need for llama3 42b v0?
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: the best quant that fits is Q3_K_M (21.0 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_S (29.8 GB file, about 31.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (45.9 GB file, about 48.0 GB in use).
Which llama3 42b v0 quant should you choose?
Q4_K_M is the usual starting point for llama3 42b v0: it balances file size and quality well. Here it is a 26.1 GB file.
The Q8_0 file is 45.9 GB, about 1.8 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 Q2_K at 16.3 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 llama3 42b v0
How much VRAM does llama3 42b v0 need?
About 28.2 GB at Q4_K_M with an 8K context window. That is the 26.1 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 llama3 42b v0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama3 42b v0 GGUF?
It depends on the quant: Q2_K is 16.3 GB, IQ3_XS is 18.1 GB, Q3_K_S is 19.0 GB, IQ3_S is 19.0 GB, IQ3_M is 19.6 GB, Q3_K_M is 21.0 GB and 8 more.
What context length does llama3 42b v0 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.
Where can I download llama3 42b v0 GGUF?
The files are on Hugging Face in the mradermacher/llama3-42b-v0-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 llama3 42b v0 use?
Hugging Face lists the license as llama3. 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 Q4_K_M on 8 GB VRAM?
No. Q4_K_M requires about 28.2 GB of VRAM at 8K context.
Does this model support vision?
No, it has no vision capabilities.
Is it trained on instruction data?
No, it is an untrained base model and should not be used with instruction prompts.