XL

Models Salesforce xLAM 8x22b R

XlamGGUF by MaziyarPanahiUpdated 2024-09-06
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant23.1 GB
Quick answer

Models Salesforce xLAM 8x22b R needs about 40.7 GB of memory at Q4_K_M (a 38.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 13 quants, from 23.1 GB (Q5_K_M) to 75.5 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Salesforce xLAM 8x22b R – 141B param Llama model with tool support

Model contains 141B parameters and is a mixture of experts. It supports a 65536 token context window and is licensed under cc‑by‑nc‑4.0. The model is available in multiple GGUF quantizations for different memory budgets.

Good at

  • Tool usage
  • Large context handling
  • High‑capacity reasoning

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • CC‑BY‑NC license limits commercial use

Best for

  • Developing tool‑integrated assistants
  • Long‑form content generation
  • Complex reasoning tasks

Who it’s for. Engineers and researchers building local LLM applications that need extensive context and tool integration. The model is suitable for non‑commercial projects due to its license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M23.1 GB 25.5 GB
Too big Get file →
IQ1_S29.7 GB 32.0 GB
Too big Get file →
IQ1_M32.7 GB 35.1 GB
Too big Get file →
Q4_K_M38.4 GB (2 parts) 40.7 GB
Too big Get file →
IQ2_XS42.0 GB 44.4 GB
Too big Get file →
Q3_K_S42.4 GB (3 parts) 44.7 GB
Too big Get file →
Q4_K_S43.2 GB (3 parts) 45.6 GB
Too big Get file →
Q2_K52.1 GB (5 parts) 54.5 GB
Too big Get file →
Q3_K_M53.0 GB (4 parts) 55.4 GB
Too big Get file →
Q3_K_L56.7 GB (4 parts) 59.1 GB
Too big Get file →
IQ3_XS58.2 GB (5 parts) 60.6 GB
Too big Get file →
Q5_K_S74.5 GB (4 parts) 76.9 GB
Too big Get file →
IQ4_XS75.5 GB (5 parts) 77.9 GB
Too big Get file →

For 8‑GB VRAM, use Q5_K_M (23.08 GB file, 25.5 GB memory). For 12‑GB VRAM, Q4_K_M (38.37 GB file, 40.7 GB memory) split into 2 shards is recommended. For 16‑GB VRAM, Q3_K_S (42.36 GB file, 44.7 GB memory) split into 3 shards offers a balance of size and performance.

What GPU do you need for Models Salesforce xLAM 8x22b R?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ1_S (29.7 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.2 GB file, about 45.6 GB in use).

Which Models Salesforce xLAM 8x22b R quant should you choose?

Q4_K_M is the usual starting point for Models Salesforce xLAM 8x22b R: it balances file size and quality well. Here it is a 38.4 GB file.

If memory is tight, the smallest file is Q5_K_M at 23.1 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized byMaziyarPanahi
FamilyXlam
Downloads (HF)1,232
Last updated2024-09-06

Frequently asked questions about Models Salesforce xLAM 8x22b R

How much VRAM does Models Salesforce xLAM 8x22b R need?

About 40.7 GB at Q4_K_M with an 8K context window. That is the 38.4 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 Models Salesforce xLAM 8x22b R on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Models Salesforce xLAM 8x22b R GGUF?

It depends on the quant: Q5_K_M is 23.1 GB, IQ1_S is 29.7 GB, IQ1_M is 32.7 GB, Q4_K_M is 38.4 GB, IQ2_XS is 42.0 GB, Q3_K_S is 42.4 GB and 7 more.

What context length does Models Salesforce xLAM 8x22b R support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Models Salesforce xLAM 8x22b R GGUF?

The files are on Hugging Face in the MaziyarPanahi/xLAM-8x22b-r-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 Models Salesforce xLAM 8x22b R use?

Hugging Face lists the license as cc-by-nc-4.0. 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, the Q5_K_M quantization requires about 25.5 GB memory at 8‑k context, which is beyond 8 GB VRAM, so it is not feasible on 8 GB VRAM.

Does this model support vision?

No, the model does not have vision capabilities.

Is this model free to use commercially?

No, it is licensed under cc‑by‑nc‑4.0, which prohibits commercial use.

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Xlam models

All Xlam →

Other large models

All large models →