Apex-35B-V1.0 APEX-I MiniPlus V2.1

APEX Quantization Series by IsValorum

Support on Ko-fi

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.

Family cross-links

Tier Footprint Base
MiniPlus 15.23 GB (14.18 GiB) Base
NanoPlus 13.03 GB (12.13 GiB) Base

Architecture and precision

  • Base model: Apexintelligence-AI/Apex-35B-V1.0 (Apache-2.0). BF16 single GGUF reference from prithivMLmods/Apex-35B-V1.0-MXFP4-MoE-GGUF.
  • Architecture: 40 layers, 30 linear-attention/SSM + 10 full-attention; 256 routed experts + 1 shared, 8 active; hidden 2048; expert FF 512; 262,144-token context; 248,320 vocab; 753 tensors including the MTP block 40.
  • iMatrix: public Apexintelligence-AI_Apex-35B-V1.0-imatrix.gguf by bartowski, 384,343,168 bytes, SHA256 b1f64857f0fa390657d8e9155e0bb0ac39ba7503b1f9dbd3c5705237016440e3, verified before use.
  • Recurrent shielding: ssm_alpha, ssm_a, ssm_dt.bias, ssm_conv1d and RMSNorms remain F32.
  • Layer 0: no special boundary; the same SSM types as the rest of the layers.
  • MTP: block 40, 20 tensors; F32 norms, Q4_K q/k/v and nextn.eh_proj, Q6_K output, Q4_0 routed experts, Q5_K shared experts. No DSpark draft is included for this family.
  • Vision projector: this repository ships the text GGUF; the upstream mmproj-Apexintelligence-AI_Apex-35B-V1.0-bf16.gguf companion is not included.

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; stable syntax and bracket behavior.
Global Embeddings token_embd.weight 1 Q4_K High-fidelity vocabulary representation.
All Normalizations output_norm, attn_*_norm, post_attention_norm, ssm_norm + MTP norms 138 F32 Uncompressed numerical stability across all 40 layers plus block 40.
Expert Routers blk.*.ffn_gate_inp, ffn_gate_inp_shexp (40 layers + MTP) 82 F32 Uncompressed routing over 256 experts; zero router drift.
Attention Gates blk.*.attn_gate.weight (30 Hybrid Layers) 30 Q8_0 High-precision gating across the hybrid linear-attention layers.
Shared Foundation Experts blk.*.ffn_{gate,down,up}_shexp (All 40 Layers) 120 Q5_K Active on every token; protected in high precision.
Periodic Full Attention blk.{3,7,11,...}.attn_q/k/v (10 Anchor Layers) 30 Q4_K Full quadratic-attention anchors for deep retrieval.
Periodic Full Attention blk.{3,7,11,...}.attn_output (10 Anchor Layers) 10 Q6_K Armored attention output projection over long context.
Recurrent SSM Scales blk.*.ssm_alpha, ssm_a, ssm_conv1d, ssm_dt 120 F32 F32 shielding against recurrent-state drift.
Linear Attention & SSM blk.*.attn_qkv, ssm_beta, ssm_out 90 Q3_K Linear-attention projections kept lean for CPU execution.
Edge MoE Experts Layers 0-9 & 30-39 (ffn_*_exps) 60 Q3_K Routed experts calibrated with the importance matrix.
Core MoE Experts Layers 10-29 (ffn_*_exps) 60 IQ3_XXS Deep-band routed experts calibrated with the importance matrix.
MTP Block 40 blk.40.{attn_output,attn_q/k/v,nextn.eh_proj,ffn_*_exps,ffn_*_shexp} 11 Q6_K output; Q4_K q/k/v + eh_proj; Q4_0 routed experts; Q5_K shared Companion MTP head; 20 tensors total including its 7 F32 norms and 2 routers counted above.

The Qty column sums to 753. The complete audited list is tensor-map.tsv.

Downloads last month
1,427
GGUF
Model size
36B params
Architecture
qwen35moe
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for IsValorum/Apex-35B-V1.0-APEX-I-MiniPlus-V2.1-GGUF

Quantized
(14)
this model

Collection including IsValorum/Apex-35B-V1.0-APEX-I-MiniPlus-V2.1-GGUF