MO

Moistral-11B-v5b

MoistralGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters10.7B
Context8K
Layers48
Architecturellama
Smallest quant2.4 GB
Quick answer

Moistral-11B-v5b 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 21 quants, from 2.4 GB (IQ1_S) to 8.8 GB (Q6_K).

Moistral‑11B‑v5b – 10.7B parameter llama model in GGUF format

Moistral‑11B‑v5b is a 10.7B parameter llama architecture model. It is available in multiple quantized GGUF files ranging from IQ1_S to Q6_K. The model supports a 8192 token context window.

Good at

  • Large context handling
  • Versatile quant options
  • Compact file sizes

Limits

  • No license information provided
  • No vision support
  • No mixture of experts

Best for

  • Local inference on limited VRAM
  • Fine‑tuning with llama.cpp
  • Rapid prototyping of language tasks

Who it’s for. Developers and researchers who need a 10.7B llama model for local inference. The model is suitable for those using llama.cpp and requiring a variety of quantization options to fit different hardware constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 4.5 GB
Fits Get file →
IQ1_M2.6 GB 4.7 GB
Fits Get file →
IQ2_XXS2.9 GB 5.0 GB
Fits Get file →
IQ2_XS3.2 GB 5.3 GB
Fits Get file →
IQ2_S3.4 GB 5.5 GB
Fits Get file →
IQ2_M3.7 GB 5.8 GB
Fits Get file →
Q2_K4.0 GB 6.1 GB
Fits Get file →
IQ3_XXS4.2 GB 6.3 GB
Fits Get file →
IQ3_XS4.4 GB 6.6 GB
Fits Get file →
Q3_K_S4.7 GB 6.8 GB
Fits Get file →
IQ3_S4.7 GB 6.8 GB
Fits Get file →
IQ3_M4.8 GB 7.0 GB
Fits Get file →
Q3_K_M5.2 GB 7.3 GB
Tight Get file →
Q3_K_L5.7 GB 7.8 GB
Tight Get file →
IQ4_XS5.8 GB 7.9 GB
Tight Get file →
Q4_06.1 GB 8.2 GB
Too big Get file →
Q4_K_S6.1 GB 8.2 GB
Too big Get file →
Q4_K_M6.5 GB 8.6 GB
Too big Get file →
Q5_K_S7.4 GB 9.5 GB
Too big Get file →
Q5_K_M7.6 GB 9.7 GB
Too big Get file →
Q6_K8.8 GB 10.9 GB
Too big Get file →

For 8 GB VRAM, use IQ4_XS (file size 5.77 GB, memory 7.9 GB) or Q4_K_S (6.12 GB, 8.2 GB). If 12 GB VRAM is available, Q4_K_M (6.46 GB, 8.6 GB) or Q5_K_S (7.4 GB, 9.5 GB) provide higher quality. All estimates are approximate.

What GPU do you need for Moistral-11B-v5b?

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: the best quant that fits is IQ2_M (3.7 GB file, about 5.8 GB in use).
  • 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).

Which Moistral-11B-v5b quant should you choose?

Q4_K_M is the usual starting point for Moistral-11B-v5b: it balances file size and quality well. Here it is a 6.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.4 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 context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyMoistral
Downloads (HF)2,461
Last updated2024-08-02

Frequently asked questions about Moistral-11B-v5b

How much VRAM does Moistral-11B-v5b 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 Moistral-11B-v5b 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 Moistral-11B-v5b GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, IQ2_S is 3.4 GB, IQ2_M is 3.7 GB and 15 more.

What context length does Moistral-11B-v5b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download Moistral-11B-v5b GGUF?

The files are on Hugging Face in the mradermacher/Moistral-11B-v5b-i1-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 Moistral‑11B‑v5b on 8 GB VRAM?

Yes, using IQ4_XS or Q4_K_S quantizations will fit within 8 GB VRAM, with memory estimates around 7.9–8.2 GB.

What quantization gives the best quality?

Higher‑bit quants such as Q5_K_S or Q6_K offer better quality, but require more memory (9.5–10.9 GB).

Is there a license restriction?

No license information is provided for this model.

Other GGUFs of Moistral-11B-v5b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Moistral models

All Moistral →

Other medium models

All medium models →