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

IsValorum/T-Search-APEX-I-NanoPlus-GGUF overview

<a href="https://ko fi.com/isvalorum" <img src="https://ko fi.com/img/githubbutton sm.svg" alt="Support on Ko fi" height="38" </a Independently computed using …

ggufquantizedquantizationapexapex-quantapex-i-nanoplusnanopluscustom-quantizationunsloth-studiomoereasoningretrievalsearch-agentllama.cppqwen35moemultimodaltext-generationconversationalenzhesfrdept

Runs locally from ~582.4 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
T-Search.APEX-I-NanoPlus.ggufGGUFGGUF12.14 GBDownload
mmproj-Q8_0.ggufGGUFQ8_0582.4 MBDownload

Model Details

Model IDIsValorum/T-Search-APEX-I-NanoPlus-GGUF
AuthorIsValorum
Pipelinetext-generation
Licenseapache-2.0
Base modelt-tech/T-Search
Last modified2026-10-19T22:12:13.000Z

Model README

---

base_model: t-tech/T-Search

base_model_relation: quantized

quantized_by: IsValorum

library_name: gguf

pipeline_tag: text-generation

language:

  • en
  • zh
  • es
  • fr
  • de
  • pt
  • it
  • ru
  • ja
  • ko
  • vi
  • th
  • ar

tags:

  • gguf
  • quantized
  • quantization
  • apex
  • apex-quant
  • apex-i-nanoplus
  • nanoplus
  • custom-quantization
  • unsloth-studio
  • moe
  • reasoning
  • retrieval
  • search-agent
  • llama.cpp
  • qwen35moe
  • multimodal

license: apache-2.0

---

<a href="https://ko-fi.com/isvalorum"><img src="https://ko-fi.com/img/githubbutton_sm.svg" alt="Support on Ko-fi" height="38"></a>

Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket.

If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies.

---

T-Search APEX-I-NanoPlus GGUF

Surgical Tensor Quantization Map (Audited from GGUF)

The exact tensor breakdown below has been verified directly from the compiled binary weights:

| Layer Group | Sub-Component / Tensor | Qty | Precision | Engineering Rationale |

| :--- | :--- | :---: | :---: | :--- |

| Global Output Head | output.weight | 1 | Q6_K | Preserves near-FP16 token classification; eliminates syntax errors, bracket drops, and hallucinations. |

| Global Embeddings | token_embd.weight | 1 | Q4_K | High-fidelity vocabulary embedding representation. |

| All Normalizations | output_norm, attn_*_norm, post_attention_norm, ssm_norm | 131 | F32 | 100% uncompressed numerical stability across all 40 layers. |

| Expert Routers | blk.*.ffn_gate_inp, ffn_gate_inp_shexp | 80 | F32 | 100% uncompressed routing fidelity across 256 micro-experts; zero router drift. |

| Attention Gates | blk.*.attn_gate.weight (30 Hybrid Layers) | 30 | Q8_0 | High-precision attention gating across hybrid DeltaNet recurrence layers; eliminates crosstalk. |

| Shared Foundation Experts | blk.*.ffn_{gate,down,up}_shexp (All 40 Layers) | 120 | Q4_K | Foundation knowledge backbone active on 100% of tokens; protected in linear Q4_K for fast streaming. |

| Periodic Full Attention | blk.{3,7,11,...}.attn_q/k/v (10 Anchor Layers) | 30 | Q4_K | Full quadratic attention anchor checkpoints for deep needle-in-a-haystack retrieval. |

| Periodic Full Attention | blk.{3,7,11,...}.attn_output (10 Anchor Layers) | 10 | Q6_K | High-precision attention output projection over deep context. |

| Recurrent SSM Scales | blk.*.ssm_alpha, ssm_a, ssm_conv1d, ssm_dt | 120 | F32 | Guarded in uncompressed FP32 to prevent DeltaNet recurrent state drift. |

| Linear Attention & SSM | blk.*.attn_qkv, ssm_beta, ssm_out | 90 | Q4_K | Linear AVX2 execution; zero SIMD CPU stalls during system RAM streaming. |

| Border MoE Down-Proj | Layers 0–1 & 38–39 (ffn_down_exps) | 4 | Q3_K | Linear SIMD execution optimized for token entry and exit stability. |

| Border MoE Gate/Up | Layers 0–1 & 38–39 (ffn_gate/up_exps) | 8 | IQ3_XXS | High-density boundary protection guided by imatrix. |

| Core MoE Down-Proj | Layers 2–37 (ffn_down_exps) | 36 | IQ3_XXS | Fortified 3.06 bpw residual stream; preserves core mathematical, coding, and reasoning capacity. |

| Core MoE Gating | Layers 2–37 (ffn_gate_exps) | 36 | IQ2_S | High-precision 2.50 bpw SwiGLU gating; eliminates activation noise. |

| Core MoE Up-Proj | Layers 2–15 (ffn_up_exps) | 14 | IQ2_S | Enhanced 2.50 bpw precision for sensitive early-intermediate feature extraction. |

| Core MoE Up-Proj | Layers 16–37 (ffn_up_exps) | 22 | IQ2_XXS | Extreme 2.06 bpw compression in deep MoE layers to reach exact 12.55 GB envelope. |

| Integrated MTP Block | blk.40.attn_output (MTP Speculative Output) | 1 | Q6_K | High-precision output for speculative draft token validation. |

| Integrated MTP Block | blk.40.nextn.eh_proj, blk.40.attn_q/k/v | 4 | Q4_K | Guarded hidden projection and attention matrices. |

| Integrated MTP Block | blk.40.ffn_down/gate/up_exps | 3 | Q4_0 | Linear quantization for fast speculative forward passes. |

| Integrated MTP Norms | blk.40._norm, nextn._norm, blk.40.ffn_gate_inp* | 12 | F32 | 100% uncompressed numerical stability in speculative routing and RMSNorms. |

The complete 100% audited tensor list is attached in tensor-map.tsv in this repository (753 / 753 tensors).

---

Community Compute Fund & Student Support

<a href="https://ko-fi.com/isvalorum"><img src="https://huggingface.co/spaces/IsValorum/MiniPlus-NanoPlus-Requests/resolve/main/assets/dance-gold-ship.gif" alt="Gold Ship dancing" width="128" align="right"></a>

All IsValorum quantizations will always remain completely free and open to the public without paywalls.

However, cloud GPU compute is expensive and funded entirely out-of-pocket. If you find these handcrafted builds to be of high quality and they benefit your day-to-day workflow, you can support future Day-0 releases on Ko-fi. Every contribution directly funds the cloud compute hours required for new model runs and helps support my university education:

<a href="https://ko-fi.com/isvalorum"><img src="https://ko-fi.com/img/githubbutton_sm.svg" alt="Support on Ko-fi" height="38"></a>

(When supporting on Ko-fi, feel free to leave a note with your Hugging Face handle and the specific model you would like prioritized).

<div style="clear: both;"></div>

Run IsValorum/T-Search-APEX-I-NanoPlus-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