SI

Simsema_Small 4 119B 32226

SimsemaGGUF by mradermacherUpdated 2026-03-28
Download on Hugging Face
Parameters119B
Context1024K
Layers36
Architecturemistral4
Smallest quant0.1 GB
Quick answer

Simsema_Small 4 119B 32226 needs about 73.0 GB of memory at Q4_K_M (a 72.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.1 GB to 97.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

Simsema Small 4 119B multimodal LLM with 256k context

Simsema Small 4 is a 119B parameter model built on the mistral4 architecture. It supports text and image input, function calls, and a 256k token context window. The model is released under Apache‑2.0 and is available in many GGUF quantizations.

Good at

  • Multimodal text and image processing
  • Large context handling
  • Function calling and JSON output

Limits

  • Requires 256k context window
  • No explicit vision support in quant list
  • Large memory footprint for high‑precision quants

Best for

  • Chatbots needing long context
  • Image‑based question answering
  • Agentic workflows with function calls

Who it’s for. Developers building chat or agent applications that require large context and multimodal input. The model is suitable for both research and production use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.0 GB
Fits Get file →
IQ1_S24.0 GB 24.8 GB
Too big Get file →
IQ1_M26.7 GB 27.5 GB
Too big Get file →
IQ2_XXS31.2 GB 32.0 GB
Too big Get file →
IQ2_XS34.8 GB 35.6 GB
Too big Get file →
IQ2_S35.2 GB 36.0 GB
Too big Get file →
IQ2_M38.8 GB 39.6 GB
Too big Get file →
Q2_K_S40.4 GB 41.2 GB
Too big Get file →
Q2_K43.4 GB 44.2 GB
Too big Get file →
IQ3_XXS45.8 GB 46.7 GB
Too big Get file →
IQ3_XS48.7 GB 49.5 GB
Too big Get file →
IQ3_S51.4 GB 52.2 GB
Too big Get file →
Q3_K_S51.4 GB 52.2 GB
Too big Get file →
IQ3_M52.1 GB 52.9 GB
Too big Get file →
Q3_K_M56.9 GB 57.8 GB
Too big Get file →
Q3_K_L61.6 GB 62.4 GB
Too big Get file →
IQ4_XS63.4 GB 64.3 GB
Too big Get file →
Q4_067.4 GB 68.2 GB
Too big Get file →
Q4_K_S67.7 GB 68.5 GB
Too big Get file →
Q4_K_M72.2 GB 73.0 GB
Too big Get file →
Q4_174.5 GB 75.4 GB
Too big Get file →
Q5_K_S81.9 GB 82.8 GB
Too big Get file →
Q5_K_M84.5 GB 85.4 GB
Too big Get file →
Q6_K97.7 GB 98.5 GB
Too big Get file →

For 8 GB VRAM, the IQ1_S quant (23.99 GB file, 24.8 GB memory at 8k context) is the smallest practical option. If 16 GB VRAM is available, IQ2_XXS (31.18 GB file, 32 GB memory) or Q2_K_S (40.4 GB file, 41.2 GB memory) provide better quality. Larger quants such as Q5_K_M or Q6_K exceed typical consumer GPU limits.

What GPU do you need for Simsema_Small 4 119B 32226?

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: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (31.2 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XXS (45.8 GB file, about 46.7 GB in use).

Which Simsema_Small 4 119B 32226 quant should you choose?

Q4_K_M is the usual starting point for Simsema_Small 4 119B 32226: it balances file size and quality well. Here it is a 72.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral4
Parameters119B (approximate, mixture of experts)
Layers36
Trained context1,048,576 tokens
KV cache (fp16)41 KB per token

Source

Quantized bymradermacher
FamilySimsema
Licenseapache-2.0
Downloads (HF)828
Last updated2026-03-28

Frequently asked questions about Simsema_Small 4 119B 32226

How much VRAM does Simsema_Small 4 119B 32226 need?

About 73.0 GB at Q4_K_M with an 8K context window. That is the 72.2 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 Simsema_Small 4 119B 32226 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Simsema_Small 4 119B 32226 GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 24.0 GB, IQ1_M is 26.7 GB, IQ2_XXS is 31.2 GB, IQ2_XS is 34.8 GB, IQ2_S is 35.2 GB and 18 more.

What context length does Simsema_Small 4 119B 32226 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.4 GB at 32K.

Where can I download Simsema_Small 4 119B 32226 GGUF?

The files are on Hugging Face in the mradermacher/Simsema_Small-4-119B-32226-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 Simsema_Small 4 119B 32226 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 Simsema Small 4 on 8 GB VRAM?

The smallest quant, IQ1_S, requires about 24.8 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support image input?

Yes, the model accepts image input and outputs text, but the provided GGUF files do not include separate vision weights.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of Simsema_Small-4-119B-32226

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Simsema models

All Simsema →

Other large models

All large models →