FI

Fimbulvetr 40

FimbulvetrGGUF by mradermacherUpdated 2024-09-18
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant4.0 GB
Quick answer

Fimbulvetr 40 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 4.0 GB (Q2_K) to 21.5 GB (F16).

Fimbulvetr 40 – a 10.7B llama model in GGUF format

Fimbulvetr 40 is a 10.7B parameter llama model merged from multiple sources. It is available in a range of static and IQ quantizations. The model supports a 4096 token context window.

Good at

  • Large context handling
  • Efficient inference with low‑bit quants
  • Versatile language generation

Limits

  • No vision capabilities
  • License not specified
  • Requires 8k context for memory estimates

Best for

  • Chatbot back‑ends
  • Text summarization
  • Code generation

Who it’s for. Developers needing a compact llama model for local inference. The model is suitable for users with limited GPU memory who can choose an appropriate quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.0 GB 5.3 GB
Fits Get file →
IQ3_XS4.4 GB 5.8 GB
Fits Get file →
Q3_K_S4.7 GB 6.0 GB
Fits Get file →
IQ3_S4.7 GB 6.0 GB
Fits Get file →
IQ3_M4.8 GB 6.2 GB
Fits Get file →
Q3_K_M5.2 GB 6.5 GB
Fits Get file →
Q3_K_L5.7 GB 7.0 GB
Fits Get file →
IQ4_XS5.8 GB 7.1 GB
Fits Get file →
Q4_K_S6.1 GB 7.4 GB
Tight Get file →
Q4_K_M6.5 GB 7.8 GB
Tight Get file →
Q5_K_S7.4 GB 8.7 GB
Too big Get file →
Q5_K_M7.6 GB 8.9 GB
Too big Get file →
Q6_K8.8 GB 10.1 GB
Too big Get file →
Q8_011.4 GB 12.7 GB
Too big Get file →
F1621.5 GB 22.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (6.12 GB file, ~8.2 GB memory) or Q4_K_M (6.46 GB file, ~8.6 GB memory). If 12 GB VRAM is available, Q5_K_S (7.4 GB file, ~9.5 GB memory) or Q5_K_M (7.6 GB file, ~9.7 GB memory) provide higher quality. For 16 GB VRAM, Q6_K (8.81 GB file, ~10.9 GB memory) or Q8_0 (11.4 GB file, ~13.5 GB memory) are options.

What GPU do you need for Fimbulvetr 40?

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 IQ4_XS (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (21.5 GB file, about 23.6 GB in use).

Which Fimbulvetr 40 quant should you choose?

Q4_K_M is the usual starting point for Fimbulvetr 40: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 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 4.0 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
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
Downloads (HF)1,486
Last updated2024-09-18

Frequently asked questions about Fimbulvetr 40

How much VRAM does Fimbulvetr 40 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Fimbulvetr 40 on an 8 GB GPU?

Yes, with IQ4_XS: the 5.8 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 Fimbulvetr 40 GGUF?

It depends on the quant: Q2_K is 4.0 GB, IQ3_XS is 4.4 GB, Q3_K_S is 4.7 GB, IQ3_S is 4.7 GB, IQ3_M is 4.8 GB, Q3_K_M is 5.2 GB and 9 more.

What context length does Fimbulvetr 40 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download Fimbulvetr 40 GGUF?

The files are on Hugging Face in the mradermacher/Fimbulvetr-40-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 Fimbulvetr 40 on 8 GB VRAM?

Yes, use Q4_K_S or Q4_K_M quants; they fit within 8 GB VRAM with the estimated memory usage.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 4096 token context window.

Other GGUFs of Fimbulvetr-40

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Fimbulvetr models

All Fimbulvetr →

Other medium models

All medium models →