NE

Nemotron 3 8b Chat 4k Sft Hf

NemotronGGUF by mradermacherUpdated 2024-08-16
Download on Hugging Face
Parameters8.54B
Context4K
Layers32
Architecturenemotron
Smallest quant3.7 GB
Quick answer

Nemotron 3 8b Chat 4k Sft Hf needs about 10.2 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 3.7 GB (Q2_K) to 17.1 GB (F16).

Nemotron 3 8b Chat 4k Sft Hf – 8.54B parameter chat model

Nemotron 3 8b Chat 4k Sft Hf is a 8.54B parameter language model trained on a 4096 token context. It is available in multiple GGUF quantizations for efficient local deployment. The model supports general-purpose text generation.

Good at

  • Short‑form chat
  • Contextual Q&A
  • Text completion

Limits

  • No vision support
  • License not specified
  • Requires 8k context for full performance

Best for

  • Building lightweight chatbots
  • Generating short articles
  • Rapid prototyping of LLM apps

Who it’s for. Developers and researchers who need a compact chat model for local inference. The model is suitable for environments with limited GPU memory and for users who prefer GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.7 GB 6.3 GB
Fits Get file →
IQ3_XS4.0 GB 6.6 GB
Fits Get file →
IQ3_S4.1 GB 6.7 GB
Fits Get file →
Q3_K_S4.1 GB 6.7 GB
Fits Get file →
IQ3_M4.3 GB 6.9 GB
Fits Get file →
Q3_K_M4.5 GB 7.2 GB
Fits Get file →
IQ4_XS4.9 GB 7.5 GB
Tight Get file →
Q3_K_L4.9 GB 7.6 GB
Tight Get file →
Q4_K_S5.1 GB 7.8 GB
Tight Get file →
Q4_K_M5.4 GB 8.1 GB
Too big Get file →
Q5_K_S6.0 GB 8.7 GB
Too big Get file →
Q5_K_M6.2 GB 8.8 GB
Too big Get file →
Q6_K7.0 GB 9.7 GB
Too big Get file →
Q8_09.1 GB 11.7 GB
Too big Get file →
F1617.1 GB 19.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.43 GB file, ~10.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (6.2 GB file, ~11 GB memory) is a good balance. If you have 16 GB or more, Q6_K (7.01 GB file, ~11.8 GB memory) offers higher quality.

What GPU do you need for Nemotron 3 8b Chat 4k Sft Hf?

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: the best quant that fits is Q6_K (7.0 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.1 GB file, about 21.9 GB in use).

Which Nemotron 3 8b Chat 4k Sft Hf quant should you choose?

Q4_K_M is the usual starting point for Nemotron 3 8b Chat 4k Sft Hf: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 9.1 GB, about 1.7 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 3.7 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

Architecturenemotron
Parameters8.54B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyNemotron
Downloads (HF)1,012
Last updated2024-08-16

Frequently asked questions about Nemotron 3 8b Chat 4k Sft Hf

How much VRAM does Nemotron 3 8b Chat 4k Sft Hf need?

About 10.2 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 Nemotron 3 8b Chat 4k Sft Hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nemotron 3 8b Chat 4k Sft Hf GGUF?

It depends on the quant: Q2_K is 3.7 GB, IQ3_XS is 4.0 GB, IQ3_S is 4.1 GB, Q3_K_S is 4.1 GB, IQ3_M is 4.3 GB, Q3_K_M is 4.5 GB and 9 more.

What context length does Nemotron 3 8b Chat 4k Sft Hf 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 Nemotron 3 8b Chat 4k Sft Hf GGUF?

The files are on Hugging Face in the mradermacher/nemotron-3-8b-chat-4k-sft-hf-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 10.2 GB of VRAM at 8k context, which fits within an 8 GB GPU with some overhead.

Does this model support vision?

No, the model does not include vision capabilities.

What is the maximum context length?

The model was trained on 4096 tokens and supports up to 4096 tokens in context.

Other GGUFs of nemotron-3-8b-chat-4k-sft-hf

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nemotron models

All Nemotron →

Other small models

All small models →