112 lines
4.1 KiB
JSON
112 lines
4.1 KiB
JSON
{
|
||
"models": {
|
||
"kimi-k2.7": {
|
||
"layers_start": 0,
|
||
"layers_end": 60,
|
||
"hf_repo": "unsloth/Kimi-K2.7-Code",
|
||
"aliases": [
|
||
"kimi-k2.7",
|
||
"Kimi-K2.7-Code",
|
||
"unsloth/Kimi-K2.7-Code"
|
||
],
|
||
"recommended": true,
|
||
"deployment_status": "recommended",
|
||
"hf_aliases": [],
|
||
"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",
|
||
"canonical_audit_dtype": "bfloat16",
|
||
"canonical_audit_quantization": "bfloat16",
|
||
"bytes_per_layer": {
|
||
"int4": 10473383366
|
||
},
|
||
"metadata": {
|
||
"architecture": "Mixture-of-Experts (MoE)",
|
||
"total_parameters": "1T",
|
||
"activated_parameters": "32B",
|
||
"num_layers": 61,
|
||
"context_length": 256000,
|
||
"native_quantization": "int4",
|
||
"canonical_audit_dtype": "bfloat16",
|
||
"canonical_audit_quantization": "bfloat16",
|
||
"download_size_gb": 595,
|
||
"recommended_short_name": "kimi-k2.7",
|
||
"recommended_engines": [
|
||
"vLLM",
|
||
"SGLang",
|
||
"KTransformers"
|
||
]
|
||
}
|
||
},
|
||
"qwen2.5-0.5b-instruct": {
|
||
"layers_start": 0,
|
||
"layers_end": 23,
|
||
"hf_repo": "Qwen/Qwen2.5-0.5B-Instruct",
|
||
"aliases": [
|
||
"qwen2.5-0.5b",
|
||
"Qwen2.5-0.5B-Instruct",
|
||
"Qwen/Qwen2.5-0.5B-Instruct"
|
||
],
|
||
"deployment_status": "supported",
|
||
"price_per_1k_tokens": 0.002,
|
||
"input_price_per_1k_tokens": 0.002,
|
||
"output_price_per_1k_tokens": 0.002,
|
||
"hf_aliases": [],
|
||
"hf_verified_match_note": "Static 10× dev-funding markup over ~$0.20/1M commercial API reference (Qwen-class hosted rates). $0.002/1k = $2/1M blended input+output.",
|
||
"required_model_bytes": 1056964608,
|
||
"download_size_bytes": 1056964608,
|
||
"native_quantization": "bfloat16",
|
||
"canonical_audit_dtype": "bfloat16",
|
||
"canonical_audit_quantization": "bfloat16",
|
||
"bytes_per_layer": {
|
||
"bfloat16": 44040192
|
||
},
|
||
"metadata": {
|
||
"architecture": "Dense transformer (GQA)",
|
||
"total_parameters": "0.5B",
|
||
"num_layers": 24,
|
||
"context_length": 32768,
|
||
"native_quantization": "bfloat16",
|
||
"download_size_gb": 1
|
||
}
|
||
},
|
||
"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. Rates are 80% of deepinfra: input 0.00012/1k ($0.15/1M), output 0.00076/1k ($0.95/1M); price_per_1k_tokens keeps the blended 0.00044 for display/back-compat. The nightly refresher tracks both sides.",
|
||
"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
|
||
},
|
||
"input_price_per_1k_tokens": 0.00012,
|
||
"output_price_per_1k_tokens": 0.00076
|
||
}
|
||
}
|
||
} |