LL

Llama 3 Experiment v1 9B

LlamaGGUF by mradermacherUpdated 2025-02-03
Download on Hugging Face
Parameters8.9B
Context8K
Layers36
Architecturellama
Smallest quant2.2 GB
Quick answer

Llama 3 Experiment v1 9B needs about 7.2 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.2 GB (IQ1_S) to 7.3 GB (Q6_K).

Llama 3 Experiment v1 9B – 8.9B parameter model in GGUF format

Llama 3 Experiment v1 9B is a 8.9B parameter language model built from Meta‑Llama‑3‑8B‑Instruct. It was merged using passthrough merge and retains the original model’s context length of 8192 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Instruction following
  • Text generation

Limits

  • No vision support
  • License is llama3
  • No mixture of experts

Best for

  • Chatbots with 8k context
  • Prompt engineering experiments
  • Text completion tasks

Who it’s for. Developers and researchers who need a 9B parameter Llama model with a 8192 token context window. The model is suitable for local inference using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.2 GB 3.9 GB
Fits Get file →
IQ1_M2.4 GB 4.1 GB
Fits Get file →
IQ2_XXS2.6 GB 4.3 GB
Fits Get file →
IQ2_XS2.9 GB 4.6 GB
Fits Get file →
IQ2_S3.0 GB 4.7 GB
Fits Get file →
IQ2_M3.2 GB 4.9 GB
Fits Get file →
Q2_K_S3.3 GB 5.0 GB
Fits Get file →
Q2_K3.5 GB 5.2 GB
Fits Get file →
IQ3_XXS3.6 GB 5.3 GB
Fits Get file →
IQ3_XS3.9 GB 5.6 GB
Fits Get file →
Q3_K_S4.0 GB 5.7 GB
Fits Get file →
IQ3_S4.1 GB 5.8 GB
Fits Get file →
IQ3_M4.2 GB 5.9 GB
Fits Get file →
Q3_K_M4.4 GB 6.1 GB
Fits Get file →
Q3_K_L4.8 GB 6.5 GB
Fits Get file →
IQ4_XS4.9 GB 6.6 GB
Fits Get file →
Q4_05.2 GB 6.9 GB
Fits Get file →
IQ4_NL5.2 GB 6.9 GB
Fits Get file →
Q4_K_S5.2 GB 6.9 GB
Fits Get file →
Q4_K_M5.4 GB 7.2 GB
Fits Get file →
Q4_15.7 GB 7.4 GB
Tight Get file →
Q5_K_S6.2 GB 7.9 GB
Tight Get file →
Q5_K_M6.3 GB 8.1 GB
Too big Get file →
Q6_K7.3 GB 9.0 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S (2.2 GB) or IQ1_M (2.36 GB). If 12‑GB VRAM is available, Q4_K_M (5.44 GB) or Q5_K_M (6.35 GB) provide higher quality. Larger models like Q6_K (7.31 GB) require 16‑GB or more. Estimates are approximate.

What GPU do you need for Llama 3 Experiment v1 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 IQ1_S (2.2 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (4.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.2 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.3 GB file, about 9.0 GB in use).

Which Llama 3 Experiment v1 9B quant should you choose?

Q4_K_M is the usual starting point for Llama 3 Experiment v1 9B: it balances file size and quality well. Here it is a 5.4 GB file.

If memory is tight, the smallest file is IQ1_S at 2.2 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

Architecturellama
Parameters8.9B
Layers36
Trained context8,192 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)531
Last updated2025-02-03

Frequently asked questions about Llama 3 Experiment v1 9B

How much VRAM does Llama 3 Experiment v1 9B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.4 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 Llama 3 Experiment v1 9B on an 8 GB GPU?

Yes, with Q5_K_S: the 6.2 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 Llama 3 Experiment v1 9B GGUF?

It depends on the quant: IQ1_S is 2.2 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.6 GB, IQ2_XS is 2.9 GB, IQ2_S is 3.0 GB, IQ2_M is 3.2 GB and 18 more.

What context length does Llama 3 Experiment v1 9B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.2 GB at 8K and 1.2 GB at 8K.

Where can I download Llama 3 Experiment v1 9B GGUF?

The files are on Hugging Face in the mradermacher/llama-3-experiment-v1-9B-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 Llama 3 Experiment v1 9B 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations which fit within 8 GB VRAM with an estimated 3.9–4.1 GB memory usage at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a context length of 8192 tokens.

Other GGUFs of llama-3-experiment-v1-9B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →