MI

Fireball Mistral Nemo Instruct 24B merge v1 i1

MistralGGUF by mradermacherUpdated 2024-09-01
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant3.0 GB
Quick answer

Fireball Mistral Nemo Instruct 24B merge v1 i1 needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 3.0 GB (IQ1_S) to 10.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Fireball Mistral Nemo Instruct 24B merge v1 i1 – 12.2B parameter Llama model

Fireball Mistral Nemo Instruct 24B merge v1 i1 is a 12.2B parameter Llama‑style model. It supports a trained context of 1,024,000 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Long‑form instruction following
  • Large context handling
  • High token throughput

Limits

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

Best for

  • Chatbot development
  • Content generation
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑context Llama model in GGUF format. The model is suitable for local inference with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.0 GB 4.8 GB
Fits Get file →
IQ1_M3.2 GB 5.1 GB
Fits Get file →
IQ2_XXS3.6 GB 5.4 GB
Fits Get file →
IQ2_XS3.9 GB 5.8 GB
Fits Get file →
IQ2_S4.1 GB 6.0 GB
Fits Get file →
IQ2_M4.4 GB 6.3 GB
Fits Get file →
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XXS4.9 GB 6.8 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_S5.6 GB 7.4 GB
Tight Get file →
IQ3_M5.7 GB 7.6 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.7 GB 8.6 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3 GB, 4.8 GB memory) or IQ1_M (3.22 GB, 5.1 GB memory). If 12 GB VRAM is available, IQ2_M (4.44 GB, 6.3 GB memory) or Q3_K_M (6.08 GB, 7.9 GB memory) are good options. Larger models like Q5_K_M (8.73 GB, 10.6 GB memory) require 16 GB VRAM or more.

What GPU do you need for Fireball Mistral Nemo Instruct 24B merge v1 i1?

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_S (4.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).

Which Fireball Mistral Nemo Instruct 24B merge v1 i1 quant should you choose?

Q4_K_M is the usual starting point for Fireball Mistral Nemo Instruct 24B merge v1 i1: it balances file size and quality well. Here it is a 7.5 GB file.

If memory is tight, the smallest file is IQ1_S at 3.0 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Frequently asked questions about Fireball Mistral Nemo Instruct 24B merge v1 i1

How much VRAM does Fireball Mistral Nemo Instruct 24B merge v1 i1 need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Fireball Mistral Nemo Instruct 24B merge v1 i1 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 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 Fireball Mistral Nemo Instruct 24B merge v1 i1 GGUF?

It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB, IQ2_M is 4.4 GB and 18 more.

What context length does Fireball Mistral Nemo Instruct 24B merge v1 i1 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Fireball Mistral Nemo Instruct 24B merge v1 i1 GGUF?

The files are on Hugging Face in the mradermacher/Fireball-Mistral-Nemo-Instruct-24B-merge-v1-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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which estimate 4.8–5.1 GB memory at 8k context.

Does the model support vision?

No, the model does not have vision capabilities.

What is the context length?

The model was trained with a context of 1,024,000 tokens.

Other GGUFs of Fireball-Mistral-Nemo-Instruct-24B-merge-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other medium models

All medium models →