popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

new tasks, model pricing, auto quantisation, etc...

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-06 17:11:53 +03:00
parent 7f67e29d76
commit ccb69c41e3
14 changed files with 466 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
packages/tracker/meshnet_tracker/model_presets.json
View File

@@ -12,7 +12,7 @@
"recommended": true,
"deployment_status": "recommended",
"hf_aliases": [],
"hf_verified_match_note": "Pending human curation (issue 23) — no HF inference-marketplace listing has been confirmed as a comparable params/quantization match for this preset yet. Leave empty until a human signs off; an empty hf_aliases list keeps this model on the static default price.",
"hf_verified_match_note": "Pending human curation (issue 23) \u2014 no HF inference-marketplace listing has been confirmed as a comparable params/quantization match for this preset yet. Leave empty until a human signs off; an empty hf_aliases list keeps this model on the static default price.",
"required_model_bytes": 638876385280,
"download_size_bytes": 638876385280,
"native_quantization": "int4",
@@ -38,6 +38,41 @@
"KTransformers"
]
}
},
"qwen3.6-35b-a3b": {
"layers_start": 0,
"layers_end": 39,
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
"aliases": [
"qwen3.6-35b-a3b",
"Qwen3.6-35B-A3B",
"unsloth/Qwen3.6-35B-A3B",
"Qwen/Qwen3.6-35B-A3B"
],
"recommended": true,
"deployment_status": "recommended",
"price_per_1k_tokens": 0.00044,
"hf_aliases": [
"qwen/qwen3.6-35b-a3b"
],
"hf_verified_match_note": "Verified 2026-07-06: unsloth/Qwen3.6-35B-A3B is a bf16 mirror of Qwen/Qwen3.6-35B-A3B; deepinfra and featherless-ai serve the official weights on the HF inference marketplace, so their rates are a fair comparable. Static price 0.00044 = 80% of deepinfra's blended $0.55/1M ($0.15 in / $0.95 out); the nightly refresher keeps it tracking.",
"required_model_bytes": 71903776776,
"download_size_bytes": 71903776776,
"native_quantization": "bfloat16",
"canonical_audit_dtype": "bfloat16",
"canonical_audit_quantization": "bfloat16",
"bytes_per_layer": {
"bfloat16": 1797594419
},
"metadata": {
"architecture": "Mixture-of-Experts (MoE, hybrid linear attention)",
"total_parameters": "35B",
"activated_parameters": "3B",
"num_layers": 40,
"context_length": 262144,
"native_quantization": "bfloat16",
"download_size_gb": 72
}
}
}
}
}