Denkwerk
quantization advice
For every llama.cpp file type, weights = parameters × effective bits per weight (measured on Llama-3.1-8B, tools/quantize/README.md, commit ad1b88c) plus KV cache and overhead (same formulas as vram-estimate) are compared with the memory budget. Quality comes from the perplexity increase that llama.cpp publishes per type in tools/quantize/quantize.cpp (Llama-3-8B, commit 732707d): tiers near_lossless ≤ 0.03, high ≤ 0.2, balanced ≤ 0.7, low above (tier limits are this service's convention)..
POST https://denk.halowerk.com/v1/quantization-adviceInputs
| Field | Type | Required | Description |
|---|---|---|---|
| hf_model | string | No | Hugging Face model id; config.json and the safetensors parameter count are read from the Hub. |
| params_b | number | No | Total parameters in billions (overrides the Hub value). |
| n_layers | integer | No | Number of transformer layers. |
| n_heads | integer | No | Attention (query) heads. |
| n_kv_heads | integer | No | Key/value heads (GQA); defaults to n_heads. |
| head_dim | integer | No | Dimension per head; defaults to hidden_size / n_heads. |
| hidden_size | integer | No | Model width. |
| vocab_size | integer | No | Vocabulary size (for the compute buffer). |
| gpu | string | No | |
| vram_gib | number | No | Usable memory per GPU in GiB. |
| n_gpus | integer | No | |
| ram_gib | number | No | System RAM available for offloaded layers. |
| context_tokens | integer | No | |
| batch | integer | No | |
| kv_cache_type | string | No | |
| overhead_gib | number | No | |
| min_quality | string | No | |
| allow_imatrix | boolean | No | Allow types that require an importance matrix. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"hf_model": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,95}/[A-Za-z0-9][A-Za-z0-9._-]{0,95}$",
"description": "Hugging Face model id; config.json and the safetensors parameter count are read from the Hub."
},
"params_b": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 5000,
"description": "Total parameters in billions (overrides the Hub value)."
},
"n_layers": {
"type": "integer",
"minimum": 1,
"maximum": 1000,
"description": "Number of transformer layers."
},
"n_heads": {
"type": "integer",
"minimum": 1,
"maximum": 1024,
"description": "Attention (query) heads."
},
"n_kv_heads": {
"type": "integer",
"minimum": 1,
"maximum": 1024,
"description": "Key/value heads (GQA); defaults to n_heads."
},
"head_dim": {
"type": "integer",
"minimum": 1,
"maximum": 4096,
"description": "Dimension per head; defaults to hidden_size / n_heads."
},
"hidden_size": {
"type": "integer",
"minimum": 1,
"maximum": 131072,
"description": "Model width."
},
"vocab_size": {
"type": "integer",
"minimum": 1,
"maximum": 2000000,
"description": "Vocabulary size (for the compute buffer)."
},
"gpu": {
"type": "string",
"enum": [
"h100-sxm",
"h100-nvl",
"h200-sxm",
"h200-nvl",
"a100-80gb-sxm",
"a100-80gb-pcie",
"a100-40gb-sxm",
"a100-40gb-pcie",
"l40s",
"l40",
"l4",
"a10",
"t4",
"rtx-a6000",
"rtx-4090",
"rtx-3090",
"apple-m2-ultra",
"apple-m4-max",
"apple-m4-pro"
]
},
"vram_gib": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 100000,
"description": "Usable memory per GPU in GiB."
},
"n_gpus": {
"type": "integer",
"minimum": 1,
"maximum": 64,
"default": 1
},
"ram_gib": {
"type": "number",
"minimum": 0,
"maximum": 100000,
"description": "System RAM available for offloaded layers."
},
"context_tokens": {
"type": "integer",
"minimum": 1,
"maximum": 4194304,
"default": 4096
},
"batch": {
"type": "integer",
"minimum": 1,
"maximum": 4096,
"default": 1
},
"kv_cache_type": {
"type": "string",
"enum": [
"f32",
"f16",
"bf16",
"fp8",
"q8_0",
"q5_1",
"q5_0",
"q4_1",
"q4_0",
"iq4_nl"
],
"default": "f16"
},
"overhead_gib": {
"type": "number",
"minimum": 0,
"maximum": 64,
"default": 0.5
},
"min_quality": {
"type": "string",
"enum": [
"near_lossless",
"high",
"balanced",
"any"
],
"default": "balanced"
},
"allow_imatrix": {
"type": "boolean",
"default": true,
"description": "Allow types that require an importance matrix."
}
}
}Published input example
{
"params_b": 8.03,
"n_layers": 32,
"n_kv_heads": 8,
"head_dim": 128,
"vram_gib": 8,
"min_quality": "high"
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.
More endpoints in this hub
- Denkwerk0.003 USDC
agent card generate
POSThttps://denk.halowerk.com/v1/agent-card-generateBuilds an Agent2Agent protocol Agent Card with protocolVersion, name, description, url, version, capabilities, default input/output modes and skills. Skills come from the supplied list or are derived from OpenAPI operations (operationId, su
- Denkwerk0.003 USDC
agent permission diff
POSThttps://denk.halowerk.com/v1/agent-permission-diffTakes the tool names (with optional descriptions) and permission scopes of an agent before and after a change and reports added and removed tools and scopes, classifies new capabilities by risk (payments, sending messages, deleting or writi
- Denkwerk0.003 USDC
annotation guide draft
POSThttps://denk.halowerk.com/v1/annotation-guide-draftTakes example texts per label and derives, without a language model, the most distinguishing terms per label (TF-IDF contrast against the other labels), representative examples, cross-label example pairs with high similarity that need a wri