Axion-1.0 35B - 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.

Vision: this repo ships the text GGUF. For multimodal use, grab Axion-1.0-35B.mmproj-bf16.gguf (or its quantized versions) from the upstream GGUF repo.

MTP/DSpark: the main GGUF has no MTP tensors and no DSpark draft is included for this family.

Family cross-links

Tier File Base Status
MiniPlus Axion-1.0-35B.APEX-I-MiniPlus-V2.1.gguf Axion-1.0-35B Published
NanoPlus see repo Axion-1.0-35B Published

Architecture and precision

  • Base model: Axion1-0/Axion-1.0-35B (Apache-2.0). BF16 GGUF reference from prithivMLmods/Axion-1.0-35B-GGUF.
  • Architecture: 40 layers, 30 linear-attention/SSM + 10 full-attention; 256 routed experts + 1 shared, 8 active; hidden 2048; 262,144-token context; 248,320 vocab.
  • iMatrix: public Axion-1.0-35B.imatrix.gguf by mradermacher, size and sha256 verified on download before use.
  • Recurrent shielding: ssm_alpha, ssm_a, ssm_dt.bias, ssm_conv1d and RMSNorms remain F32.
  • Layer 0: attn_gate in Q8_0; the linear-attention projections (attn_qkv, ssm_beta, ssm_out) in Q3_K.

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 131 F32 Uncompressed numerical stability across all layers.
Expert Routers blk.*.ffn_gate_inp, ffn_gate_inp_shexp 80 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 needle-in-a-haystack 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.

The machine-readable version is tensor-map.tsv.

Files

File Size Notes
Axion-1.0-35B.APEX-I-MiniPlus-V2.1.gguf 14,751,301,312 bytes Main MiniPlus V2.1 GGUF
tensor-map.tsv 33,146 bytes Per-tensor types
chat_template.jinja from source Axion chat template

Usage

llama-cli -m Axion-1.0-35B.APEX-I-MiniPlus-V2.1.gguf -p "Hello" -ngl 99 -c 32768
llama-server -m Axion-1.0-35B.APEX-I-MiniPlus-V2.1.gguf --jinja -ngl 99 -c 32768

Limitations

  • Base benchmarks are self-reported by the Axion team; no independent evaluation is claimed for this tier.
  • Quantization quality is theoretical until you test it on your own workload.

License

Apache-2.0, inherited from the base model. See the source model card.

Downloads last month
765
GGUF
Model size
35B 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/Axion-1.0-35B-APEX-I-MiniPlus-V2.1-GGUF

Quantized
(8)
this model

Collection including IsValorum/Axion-1.0-35B-APEX-I-MiniPlus-V2.1-GGUF