yasu-oh
Llama-3-Swallow-Infused-R1776-70B
- Parameters
- 70.6B
- Max context length
- 131,072
- Architecture
- llama
- License
- Conditional
- Base model
- yasu-oh/Llama-3-Swallow-Infused-R1776-70B
- License
- llama3.3
About Llama-3-Swallow-Infused-R1776-70B
Llama-3-Swallow-Infused-R1776-70B is a GGUF model based on yasu-oh/Llama-3-Swallow-Infused-R1776-70B on Hugging Face. GGUF files are published by mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF. It has about 70.6B parameters, the llama architecture, a maximum context length of 131,072 tokens (values written in the GGUF).
There are 22 quantizations, with file sizes from 15.3 GB (IQ1_S) to 49.9 GB (Q5_K_M) (actual sizes on Hugging Face).
Running Q4_K_M (42.5 GB) with an 8,192-token context needs an estimated 46.0 GB of memory, and an estimated 54.1 GB at 32,768 tokens. For 8,192 tokens, a GPU with 48 GB or more of VRAM, or a Mac with 48 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom). The smallest, IQ1_S (15.3 GB), needs an estimated 18.8 GB at 8,192 tokens.
The original model is licensed under Llama 3.3 Community License, which allows commercial use with conditions such as scale or purpose. Check the original license for the terms of use.
File size and estimated memory per quantization
- Up to 8 GB
- Up to 16 GB
- Up to 24 GB
- Up to 48 GB
- Up to 128 GB
- More
File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.
All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).
About the "quality guide" (how far a quantization drifts from the original)
For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.
The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).
These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".
| Quantization | Quality guide | KLD (no imatrix) | KLD (imatrix) | Size (Llama-3-8B) |
|---|---|---|---|---|
| Q8_0 | Nearly identical | 0.0014 | - | 7.96 GiB |
| Q6_K | Very small | 0.0055 | - | 6.14 GiB |
| Q5_K_M | Very small | 0.0108 | - | 5.33 GiB |
| Q5_K_S | Small | 0.0166 | - | 5.21 GiB |
| Q5_1 | Small | 0.0180 | - | 5.65 GiB |
| Q5_0 | Small | 0.0222 | - | 5.21 GiB |
| Q4_K_M | Small | 0.0313 | 0.0282 | 4.58 GiB |
| Q4_K_S | Medium | 0.0431 | 0.0320 | 4.37 GiB |
| IQ4_NL | Small | - | 0.0357 | 4.35 GiB |
| IQ4_XS | Small | - | 0.0363 | 4.14 GiB |
| Q4_1 | Medium | 0.0717 | - | 4.78 GiB |
| Q4_0 | Medium | 0.0719 | - | 4.34 GiB |
| Q3_K_L | Medium | 0.0872 | 0.0731 | 4.03 GiB |
| Q3_K_M | Medium | 0.1019 | 0.0844 | 3.74 GiB |
| IQ3_M | Medium | - | 0.1025 | 3.53 GiB |
| IQ3_S | Medium | - | 0.1113 | 3.42 GiB |
| IQ3_XS | Large | - | 0.1387 | 3.28 GiB |
| IQ3_XXS | Large | - | 0.1836 | 3.05 GiB |
| Q3_K_S | Large | 0.2282 | 0.1998 | 3.41 GiB |
| IQ2_M | Large | - | 0.3260 | 2.74 GiB |
| Q2_K | Very large | 0.4451 | 0.3322 | 2.96 GiB |
| Q2_K_S | Very large | - | 0.4034 | 2.96 GiB |
| IQ2_S | Very large | - | 0.4392 | 2.56 GiB |
| IQ2_XS | Very large | - | 0.5463 | 2.43 GiB |
| IQ2_XXS | Very large | - | 0.8120 | 2.24 GiB |
| IQ1_M | Very large | - | 1.3931 | 2.01 GiB |
| IQ1_S | Very large | - | 2.2546 | 1.88 GiB |
Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations
GGUF source
mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF
Converted and published by a third party About this label
Last checked: Nov 11, 2026
- Architecture
- llama
- Supported before llama.cpp b4409
- Parameters
- 70.6B
- Max context length
- 131,072
- License
- llama3.3 Conditional
Ollama ollama run hf.co/mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF:Q4_K_M
llama.cpp llama-server -hf mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF:Q4_K_M
Generation speed on common GPUs and Macs (estimated)
A rough guide to how fast Q4_K_M (42.5 GB) generates text. Each token reads the model weights once, so the upper limit is memory bandwidth ÷ file size. The guide is 60–80% of that, where most published measurements fall.
| Device | Memory bandwidth | Guide (tokens/s) Estimated | Upper limit |
|---|---|---|---|
| Apple M5 Pro 64 GB | 307 GB/s | 4.3–5.8 | 7.2 |
| Apple M2 Max 64 GB | 400 GB/s | 5.6–7.5 | 9.4 |
| Apple M5 Ultra 96 GB | 1,200 GB/s | 17–23 | 28 |
Estimates only. Prompt processing speed (limited by compute) is not included. Longer contexts and offloading part of the model to the CPU make it slower. Macs are shown only when installed memory is at least 4/3 of what is needed. Devices without published bandwidth (some GeForce cards, etc.) are not shown.
License and commercial use
Llama 3.3 Community License Conditional
Allows commercial use. Over 700 million monthly active users requires a separate license from Meta. Redistribution and published derivatives must show "Built with Llama", and you must follow the Acceptable Use Policy.
Based on the license on the original model's Hugging Face page. Original license text (checked Oct 18, 2026)
The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses
How to run
Example commands using Q4_K_M. To use another quantization, replace the name with one from the table above. How to run local LLMs
Ollama
Run it by pointing directly at the GGUF on Hugging Face.
ollama run hf.co/mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF:Q4_K_M
llama.cpp
Pass the repository and quantization name to llama-server (or llama-cli) with -hf.
llama-server -hf mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF:Q4_K_M
LM Studio
Paste mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF into the search box, download it, and choose the quantization from the file list.
Models of a similar size (other developers)
-
79.7B
Qwen
Qwen3-Coder-Next
- Q4_K_M size
- 48.5 GB
- Memory at 8K
- 49.7 GB
Measured Estimated VRAM 48 GB+
-
70.6B
meta-llama
Llama-3.3-70B-Instruct
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
-
79.7B
Qwen
Qwen3-Next-80B-A3B-Instruct
- Q4_K_M size
- 48.5 GB
- Memory at 8K
- 49.6 GB
Measured Estimated VRAM 48 GB+
-
74B
nvidia
NVIDIA-Nemotron-3.5-Bolt-74B-A9B
- UD-IQ1_S size
- 18.5 GB
- Memory at 8K
- 19.6 GB
Measured Estimated VRAM 24 GB+
-
72.7B
Qwen
Qwen2.5-72B-Instruct
- Q4_K_M size
- 47.4 GB
- Memory at 8K
- 50.9 GB
Measured Estimated VRAM 48 GB+
-
70.6B
huihui-ai
Llama-3.3-70B-Instruct-abliterated
- Q4_K_M size
- 42.5 GB
- Memory at 8K
- 46.0 GB
Measured Estimated VRAM 48 GB+
Frequently asked questions
- How much memory do I need to run Llama-3-Swallow-Infused-R1776-70B (Q4_K_M)?
- The file size is 42.5 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 46.0 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
- Can Llama-3-Swallow-Infused-R1776-70B be used commercially?
- The original model's license is Llama 3.3 Community License (Commercial use with conditions).Allows commercial use. Over 700 million monthly active users requires a separate license from Meta. Redistribution and published derivatives must show "Built with Llama", and you must follow the Acceptable Use Policy. Check the original license text before deciding.
- Does Llama-3-Swallow-Infused-R1776-70B run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
- 8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: up to IQ2_S (est. 25.7 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
- What is the command to run Llama-3-Swallow-Infused-R1776-70B with Ollama?
- Run "ollama run hf.co/mradermacher/Llama-3-Swallow-Infused-R1776-70B-i1-GGUF:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.