midashenglm 7b 1021 needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 9 quants, from 2.0 GB (IQ1_M) to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
MidashengLM 7B 1021 – a multimodal GGUF model based on Qwen2.5-Omni
MidashengLM 7B 1021 is a 7.62 billion‑parameter multimodal model derived from Qwen2.5‑Omni. It supports text, image, audio, and video inputs and generates text and speech. The model is available in GGUF format for llama.cpp inference.
Good at
- Multimodal perception and generation
- Real‑time voice and video chat
- End‑to‑end speech instruction following
Limits
- Requires a llama.cpp fork
- No vision support in the base repo excerpt
- Large VRAM needed for higher‑quality quants
Best for
- Local multimodal inference
- Real‑time streaming applications
- Speech‑to‑text and image captioning
Who it’s for. Researchers and developers needing a local multimodal LLM that can process text, images, audio, and video. The model is suitable for applications that require real‑time voice and video interaction.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 2.0 GB | 3.0 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q2_K_S | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (2.04 GB, 3 GB memory at 8k context) or IQ2_M (2.78 GB, 3.8 GB memory). For 12 GB VRAM, Q4_K_M (4.68 GB, 5.7 GB memory) is a good balance. Higher‑quality quants such as Q8_0 (8.1 GB, 9.1 GB memory) require more VRAM.
What GPU do you need for midashenglm 7b 1021?
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 Q2_K_S (2.8 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which midashenglm 7b 1021 quant should you choose?
Q4_K_M is the usual starting point for midashenglm 7b 1021: it balances file size and quality well. Here it is a 4.7 GB file.
The Q8_0 file is 8.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_M at 2.0 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
Source
Frequently asked questions about midashenglm 7b 1021
How much VRAM does midashenglm 7b 1021 need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 midashenglm 7b 1021 on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of midashenglm 7b 1021 GGUF?
It depends on the quant: IQ1_M is 2.0 GB, IQ2_M is 2.8 GB, Q2_K_S is 2.8 GB, Q3_K_M is 3.8 GB, Q4_K_M is 4.7 GB, Q5_K_M is 5.4 GB and 3 more.
What context length does midashenglm 7b 1021 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download midashenglm 7b 1021 GGUF?
The files are on Hugging Face in the mispeech/midashenglm-7b-1021-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 midashenglm 7b 1021 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 MidashengLM 7B 1021 on 8 GB VRAM?
Yes, using IQ1_M or IQ2_M quants keeps VRAM usage below 8 GB.
Does the model support vision?
The model detects vision abilities, but the base GGUF repo does not include vision support.
What license applies to this model?
The model is released under the Apache‑2.0 license.