MU

multimaster-7b-v2

MultimasterGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters35.4B
Context32K
Layers32
Architecturellama
Smallest quant7.3 GB
Quick answer

multimaster-7b-v2 needs about 23.0 GB of memory at Q4_K_M (a 21.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.3 GB (IQ1_S) to 29.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

35.4B parameter multimaster-7b-v2, a large language model

multimaster-7b-v2 is a 35.4B parameter model built on the llama architecture. It supports a 32,768 token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • High parameter count
  • Apache‑2.0 licensed

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • No active parameters listed

Best for

  • Research on large‑context LLMs
  • Fine‑tuning with 32k context
  • Deploying on high‑VRAM GPUs

Who it’s for. Researchers and developers needing a large, open‑source language model with a 32k token context. The model is suitable for tasks that require extensive context and high capacity, such as long‑form generation or complex reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.3 GB 8.8 GB
Too big Get file →
IQ1_M8.1 GB 9.6 GB
Too big Get file →
IQ2_XXS9.3 GB 10.9 GB
Too big Get file →
IQ2_XS10.4 GB 12.0 GB
Too big Get file →
IQ2_S10.6 GB 12.2 GB
Too big Get file →
IQ2_M11.7 GB 13.2 GB
Too big Get file →
Q2_K12.9 GB 14.5 GB
Too big Get file →
IQ3_XXS13.6 GB 15.2 GB
Too big Get file →
IQ3_XS14.5 GB 16.0 GB
Too big Get file →
Q3_K_S15.3 GB 16.9 GB
Too big Get file →
IQ3_S15.3 GB 16.9 GB
Too big Get file →
IQ3_M15.6 GB 17.1 GB
Too big Get file →
Q3_K_M17.0 GB 18.5 GB
Too big Get file →
Q3_K_L18.4 GB 19.9 GB
Too big Get file →
IQ4_XS18.9 GB 20.5 GB
Too big Get file →
Q4_020.1 GB 21.6 GB
Too big Get file →
Q4_K_S20.1 GB 21.7 GB
Too big Get file →
Q4_K_M21.4 GB 23.0 GB
Too big Get file →
Q5_K_S24.4 GB 26.0 GB
Too big Get file →
Q5_K_M25.1 GB 26.7 GB
Too big Get file →
Q6_K29.1 GB 30.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.28 GB file, 8.8 GB memory). For 12 GB VRAM, IQ2_XS (10.39 GB file, 12 GB memory) is a good balance. For 16 GB VRAM, Q3_K_S (15.28 GB file, 16.9 GB memory) offers higher quality.

What GPU do you need for multimaster-7b-v2?

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: the best quant that fits is IQ2_XS (10.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (14.5 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.1 GB file, about 30.6 GB in use).

Which multimaster-7b-v2 quant should you choose?

Q4_K_M is the usual starting point for multimaster-7b-v2: it balances file size and quality well. Here it is a 21.4 GB file.

If memory is tight, the smallest file is IQ1_S at 7.3 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
Parameters35.4B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,621
Last updated2024-08-02

Frequently asked questions about multimaster-7b-v2

How much VRAM does multimaster-7b-v2 need?

About 23.0 GB at Q4_K_M with an 8K context window. That is the 21.4 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 multimaster-7b-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of multimaster-7b-v2 GGUF?

It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 8.1 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.4 GB, IQ2_S is 10.6 GB, IQ2_M is 11.7 GB and 15 more.

What context length does multimaster-7b-v2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download multimaster-7b-v2 GGUF?

The files are on Hugging Face in the mradermacher/multimaster-7b-v2-i1-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 multimaster-7b-v2 use?

Hugging Face lists the license as apache-2.0. 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 multimaster-7b-v2 on 8 GB VRAM?

Use the IQ1_S quant, which requires 8.8 GB memory at 8k context. It will fit on 8 GB VRAM with some overhead.

Does multimaster-7b-v2 support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of multimaster-7b-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Multimaster models

All Multimaster →

Other large models

All large models →