GL

GLM 5.1

GLMGGUF by unslothUpdated 2026-04-07
Download on Hugging Face
Parameters754B
Context198K
Layers79
Architectureglm-dsa
Smallest quant205.5 GB
Quick answer

GLM 5.1 needs about 466.4 GB of memory at Q4_K_M (a 464.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 205.5 GB (IQ1_M) to 1508.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM‑5.1: 754 billion‑parameter LLM for agentic tasks

GLM‑5.1 is a 754 billion‑parameter model built on the glm‑dsa architecture. It excels in coding, terminal tasks, and long‑horizon agentic reasoning. The model is released under the MIT license and supports local deployment via llama.cpp and other frameworks.

Good at

  • Long‑horizon agentic reasoning
  • Strong coding and terminal task performance
  • Iterative problem solving

Limits

  • Large VRAM requirement for high‑quality quants
  • No vision or multimodal support
  • Requires 8 k context for memory estimates

Best for

  • Developing autonomous agents
  • Complex code generation
  • Extended tool‑call workflows

Who it’s for. Engineers and researchers needing a high‑capacity LLM for agentic and coding tasks. The model is suitable for users with sufficient GPU memory to run large quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M205.5 GB (6 parts) 207.4 GB
Too big Get file →
IQ2_XXS220.6 GB (6 parts) 222.5 GB
Too big Get file →
IQ2_M236.2 GB (6 parts) 238.1 GB
Too big Get file →
Q2_K_XL252.4 GB (7 parts) 254.3 GB
Too big Get file →
IQ3_XXS268.3 GB (7 parts) 270.2 GB
Too big Get file →
IQ3_S279.6 GB (7 parts) 281.5 GB
Too big Get file →
Q3_K_S313.5 GB (8 parts) 315.4 GB
Too big Get file →
Q3_K_M338.4 GB (8 parts) 340.3 GB
Too big Get file →
Q3_K_XL340.1 GB (8 parts) 342.0 GB
Too big Get file →
IQ4_XS361.3 GB (9 parts) 363.2 GB
Too big Get file →
IQ4_NL368.9 GB (9 parts) 370.8 GB
Too big Get file →
Q4_K_S433.9 GB (10 parts) 435.8 GB
Too big Get file →
MXFP4_MOE450.9 GB (11 parts) 452.8 GB
Too big Get file →
Q4_K_M464.5 GB (11 parts) 466.4 GB
Too big Get file →
Q4_K_XL466.0 GB (11 parts) 467.9 GB
Too big Get file →
Q5_K_S525.9 GB (12 parts) 527.9 GB
Too big Get file →
Q5_K_M558.5 GB (13 parts) 560.4 GB
Too big Get file →
Q5_K_XL560.1 GB (13 parts) 562.0 GB
Too big Get file →
Q6_K621.3 GB (14 parts) 623.2 GB
Too big Get file →
Q6_K_XL684.4 GB (16 parts) 686.3 GB
Too big Get file →
Q8_0801.3 GB (17 parts) 803.3 GB
Too big Get file →
Q8_K_XL810.6 GB (18 parts) 812.5 GB
Too big Get file →
BF161508.0 GB (33 parts) 1509.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (205.54 GB file, ~207.4 GB memory at 8 k context). With 12 GB VRAM, Q4_K_S (433.9 GB file, ~435.8 GB memory) is a good balance. For 16 GB VRAM, Q4_K_XL (465.97 GB file, ~467.9 GB memory) offers higher quality.

What GPU do you need for GLM 5.1?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which GLM 5.1 quant should you choose?

Q4_K_M is the usual starting point for GLM 5.1: it balances file size and quality well. Here it is a 464.5 GB file.

The Q8_0 file is 801.3 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 205.5 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

Architectureglm-dsa
Parameters754B (approximate, mixture of experts)
Layers79
Trained context202,752 tokens
KV cache (fp16)168 KB per token

Source

Quantized byunsloth
FamilyGLM
Base modelzai-org/GLM-5.1
Licensemit
Downloads (HF)3,630
Last updated2026-04-07

Frequently asked questions about GLM 5.1

How much VRAM does GLM 5.1 need?

About 466.4 GB at Q4_K_M with an 8K context window. That is the 464.5 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 GLM 5.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 207.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.1 GGUF?

It depends on the quant: IQ1_M is 205.5 GB, IQ2_XXS is 220.6 GB, IQ2_M is 236.2 GB, Q2_K_XL is 252.4 GB, IQ3_XXS is 268.3 GB, IQ3_S is 279.6 GB and 17 more.

What context length does GLM 5.1 support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download GLM 5.1 GGUF?

The files are on Hugging Face in the unsloth/GLM-5.1-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 GLM 5.1 use?

Hugging Face lists the license as mit. 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 GLM‑5.1 on 8 GB VRAM?

Use the IQ1_M quant; it requires about 207.4 GB of VRAM at 8 k context, which is not feasible on 8 GB. You would need a larger GPU or a lower‑quality quant.

Does GLM‑5.1 support vision tasks?

No, the model has no vision or multimodal capabilities.

Other GGUFs of GLM-5.1

Similar models

Browse all →

More from unsloth

All by unsloth →

More GLM models

All GLM →

Other large models

All large models →