MI

Mistral Large Instruct 2407

MistralGGUF by legraphistaUpdated 2024-07-25
Download on Hugging Face
Parameters123B
Context32K
Layers88
Architecturellama
Smallest quant26.0 GB
Quick answer

Mistral Large Instruct 2407 needs about 58.7 GB of memory at IQ3_M (a 55.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 25 quants, from 26.0 GB (IQ1_S) to 245.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Mistral Large Instruct 2407 – 123B parameter Llama model

Mistral Large Instruct 2407 is a 123‑billion‑parameter Llama‑style model. It supports 32768‑token context and is available in multiple GGUF quantizations. The model is released under an other license.

Good at

  • Large context handling
  • Instruction following
  • High token capacity

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License not specified

Best for

  • Long‑form content generation
  • Complex instruction tasks
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑scale instruction model with flexible quantization. Suitable for local inference on capable hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S26.0 GB 29.4 GB
Too big Get file →
IQ1_M28.4 GB 31.8 GB
Too big Get file →
IQ2_XXS32.4 GB 35.9 GB
Too big Get file →
IQ2_XS36.1 GB 39.5 GB
Too big Get file →
IQ2_S38.4 GB 41.8 GB
Too big Get file →
Q2_K_S41.6 GB 45.1 GB
Too big Get file →
IQ2_M41.6 GB 45.1 GB
Too big Get file →
Q2_K45.2 GB (2 parts) 48.6 GB
Too big Get file →
IQ3_XXS47.0 GB (2 parts) 50.5 GB
Too big Get file →
IQ3_XS50.1 GB (3 parts) 53.6 GB
Too big Get file →
Q3_K_S52.8 GB (3 parts) 56.3 GB
Too big Get file →
IQ3_S53.0 GB (3 parts) 56.4 GB
Too big Get file →
IQ3_M55.3 GB (3 parts) 58.7 GB
Too big Get file →
Q3_K59.1 GB (3 parts) 62.6 GB
Too big Get file →
Q3_K_L64.6 GB (3 parts) 68.0 GB
Too big Get file →
IQ4_XS65.4 GB (3 parts) 68.9 GB
Too big Get file →
IQ4_NL69.2 GB (3 parts) 72.7 GB
Too big Get file →
Q4_K_S69.6 GB (3 parts) 73.0 GB
Too big Get file →
Q4_K73.2 GB (4 parts) 76.7 GB
Too big Get file →
Q5_K_S84.4 GB (4 parts) 87.8 GB
Too big Get file →
Q5_K86.5 GB (4 parts) 89.9 GB
Too big Get file →
Q6_K100.6 GB (5 parts) 104.0 GB
Too big Get file →
Q8_0130.3 GB (6 parts) 133.7 GB
Too big Get file →
BF16245.2 GB (11 parts) 248.7 GB
Too big Get file →
—245.2 GB (11 parts) 248.7 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (25.96 GB file, 29.4 GB memory). For 16‑GB VRAM, IQ2_S (38.38 GB file, 41.8 GB memory) or Q2_K_S (41.61 GB file, 45.1 GB memory). For 24‑GB VRAM, Q3_K (59.1 GB file, 62.6 GB memory) or Q4_K (73.22 GB file, 76.7 GB memory).

What GPU do you need for Mistral Large Instruct 2407?

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_M (28.4 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (41.6 GB file, about 45.1 GB in use).

Which Mistral Large Instruct 2407 quant should you choose?

IQ3_M (55.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 26.0 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
Parameters123B
Layers88
Trained context32,768 tokens
KV cache (fp16)352 KB per token

Source

Quantized bylegraphista
FamilyMistral
Licenseother
Downloads (HF)936
Last updated2024-07-25

Frequently asked questions about Mistral Large Instruct 2407

How much VRAM does Mistral Large Instruct 2407 need?

About 58.7 GB at IQ3_M with an 8K context window. That is the 55.3 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 Mistral Large Instruct 2407 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Large Instruct 2407 GGUF?

It depends on the quant: IQ1_S is 26.0 GB, IQ1_M is 28.4 GB, IQ2_XXS is 32.4 GB, IQ2_XS is 36.1 GB, IQ2_S is 38.4 GB, Q2_K_S is 41.6 GB and 19 more.

What context length does Mistral Large Instruct 2407 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download Mistral Large Instruct 2407 GGUF?

The files are on Hugging Face in the legraphista/Mistral-Large-Instruct-2407-IMat-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 Mistral Large Instruct 2407 use?

Hugging Face lists the license as other. 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 Mistral Large Instruct 2407 on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 29.4 GB VRAM at 8k context, which is beyond 8 GB. The model cannot run on 8 GB VRAM in any quantization.

How many shards does the Q8_0 quant have?

The Q8_0 quant is split into 6 shards.

What is the estimated VRAM usage for the Q3_K quant at 8k context?

Approximately 62.6 GB VRAM is required.

Other GGUFs of Mistral-Large-Instruct-2407

Similar models

Browse all →

More from legraphista

All by legraphista →

More Mistral models

All Mistral →

Other large models

All large models →