GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

emwesoft/GLM-5.3-NVFP4-GGUF overview

GLM 5.3 753B — NVFP4 GGUF no MTP Native GGUF of incoai/GLM 5.3 NVFP4 https://huggingface.co/incoai/GLM 5.3 NVFP4 , the vendor's ModelOpt NVFP4 repack of zai or…

ggufnvfp4glmglm-dsallama.cpptext-generationbase_model:incoai/GLM-5.3-NVFP4base_model:quantized:incoai/GLM-5.3-NVFP4license:mitendpoints_compatibleregion:usconversational

Runs locally from ~34.88 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

10 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
GLM-5.3-NVFP4-00001-of-00010.ggufGGUFGGUF42.20 GBDownload
GLM-5.3-NVFP4-00002-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00003-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00004-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00005-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00006-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00007-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00008-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00009-of-00010.ggufGGUFGGUF42.19 GBDownload
GLM-5.3-NVFP4-00010-of-00010.ggufGGUFGGUF34.88 GBDownload

Model Details

Model IDemwesoft/GLM-5.3-NVFP4-GGUF
Authoremwesoft
Pipelinetext-generation
Licensemit
Base modelzai-org/GLM-5.3,incoai/GLM-5.3-NVFP4
Last modified2026-08-29T10:34:33.000Z

Model README

---

license: mit

base_model: [zai-org/GLM-5.3, incoai/GLM-5.3-NVFP4]

pipeline_tag: text-generation

library_name: gguf

tags: [gguf, nvfp4, glm, glm-dsa, llama.cpp]

---

GLM-5.3 753B — NVFP4 GGUF (no MTP)

Native GGUF of incoai/GLM-5.3-NVFP4, the

vendor's ModelOpt NVFP4 repack of zai-org/GLM-5.3

(753B, glm-dsa, 78 blocks, hidden 6144, 256 experts). The NVFP4 weights are kept as NVFP4 —

this is not a requantisation.

445 GB, 10 shards. block_count 78, 1947 tensors, 225 NVFP4 tensors.

Related repos

| | |

|---|---|

| With MTP head | emwesoft/GLM-5.3-NVFP4-MTP-GGUF — adds block 78, enables --spec-type draft-mtp |

| DFlash2 drafters | emwesoft/GLM-5.3-DFlash2-GGUF — speculative decoding for this model |

This variant has no MTP head, so --spec-type draft-mtp is unavailable. Use the DFlash2

drafters for speculative decoding, or the MTP repo above.

Engine requirements

llama.cpp with glm-dsa + GGML_TYPE_NVFP4. Three fixes are not yet upstream:

  1. jinja numeric attribute access (obj.0) — GLM-5.3's chat template uses

m.content.0.output. Without it the template throws, caps_get() swallows it,

supports_tool_calls reports false, and every tool call comes back as plain text.

  1. glm-dsa layer-input exposure — DFlash needs res->t_layer_inp[il]; without it

attaching a drafter aborts on the first decode with GGML_ASSERT(t_layer_inp[il] != nullptr).

  1. Whitespace tolerance before </tool_call> — a stray newline makes the streaming

parser recognise a tool call then lose it, aborting from compute_diffs.

Measured throughput

2x RTX PRO 6000 Blackwell + 4x RTX 3090 + 251 GB RAM, 400K context, -t 36 -tb 40,

experts partly CPU-resident (the weights do not fit in 288 GB of VRAM):

| config | acceptance | decode |

|---|---|---|

| MTP head, n-max 3 | 74.9% (mean len 3.24) | 9.3-12.2 tok/s |

| DFlash2 Q8_0, n-max 4 | 67.7% (mean len 3.69) | 7.6-12.8 tok/s |

| no speculation | - | ~10 tok/s |

Throughput is prompt-dependent because acceptance is. Threads matter: on a 24-core/48-thread

CPU, -t 48 collapsed decode to 0.5 tok/s — the ggml threadpool busy-spins and starves the CUDA

submission thread. Leave headroom.

Sampling

From generation_config.json: temperature 1.0, top_p 0.95. The template exposes

low/high/max reasoning effort only; anything else becomes max, and thinking cannot be

disabled.

Run emwesoft/GLM-5.3-NVFP4-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models