{"id":296801,"recorded_at":"2026-10-26T21:59:58.806998Z","observed_at":"2026-10-26T21:59:58.806923Z","subject_kind":"endpoint","subject":"51f8265d-c798-400d-9016-1abaccd9eb86","kind":"mcp.tools","method":"probe.mcp/1","body":{"count":6,"tools":[{"description":"Can this GPU run this open-weight LLM? Returns fits, tight or no, the memory split (weights, KV cache, overhead), a decode-speed ceiling, the longest context that fits and, on a no, every change that would make it fit: quantisation, KV cache, context, another card or a smaller model. Model: a name or id from list_models, any Hugging Face repo id, or its architecture. GPU: a name or id from list_gpus, or vram_gb for any other card.","inputSchema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"active_params_b":{"description":"Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.","exclusiveMinimum":0,"maximum":10000,"type":"number"},"apple_silicon":{"description":"vram_gb is Apple unified memory; the GPU can use about 75% of it by default.","type":"boolean"},"architecture":{"description":"A model described by its config.json values instead of a name.","properties":{"active_params_b":{"description":"Parameters read per token, billions (mixture-of-experts only).","exclusiveMinimum":0,"maximum":10000,"type":"number"},"fixed_state_gb":{"description":"Fixed recurrent state of linear-attention or Mamba layers, GB.","maximum":100,"minimum":0,"type":"number"},"head_dim":{"description":"head_dim, or hidden_size ÷ num_attention_heads","exclusiveMinimum":0,"maximum":4096,"type":"integer"},"kv_groups":{"description":"Only for non-standard attention: one entry per group of layers that cache the same way. Replaces layers × kv_heads × head_dim.","items":{"properties":{"layers":{"exclusiveMinimum":0,"maximum":9007199254740991,"type":"integer"},"values_per_token":{"description":"Values each layer caches per token: 2 × KV heads × head dim, or the latent width for MLA.","exclusiveMinimum":0,"type":"number"},"window_tokens":{"description":"Sliding window: these layers keep only this many tokens.","exclusiveMinimum":0,"maximum":9007199254740991,"type":"integer"}},"required":["layers","values_per_token"],"type":"object"},"maxItems":8,"type":"array"},"kv_heads":{"description":"num_key_value_heads","exclusiveMinimum":0,"maximum":1024,"type":"integer"},"layers":{"description":"num_hidden_layers","exclusiveMinimum":0,"maximum":1000,"type":"integer"},"native_context":{"description":"The context window the model supports, tokens.","exclusiveMinimum":0,"maximum":9007199254740991,"type":"integer"},"params_b":{"description":"Total parameters, billions; all experts for a mixture-of-experts model.","exclusiveMinimum":0,"maximum":10000,"type":"number"}},"required":["params_b","layers","kv_heads","head_dim"],"type":"object"},"bandwidth_gb_s":{"description":"Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.","exclusiveMinimum":0,"maximum":100000,"type":"number"},"context":{"default":8192,"description":"Tokens held in context: prompt plus conversation.","maximum":10000000,"minimum":1,"type":"integer"},"gpu":{"description":"A GPU from list_gpus (id or name, e.g. \"rtx-4090\", \"4090\" or \"M4 Max\").","maxLength":100,"minLength":1,"type":"string"},"kv_cache":{"default":"fp16","description":"KV cache precision. fp16 is what most runtimes use; q8 halves the cache.","enum":["fp16","q8"],"type":"string"},"model":{"description":"A model from list_models (id or name, e.g. \"llama-3.3-70b\" or \"Llama 3.3 70B\"), or any Hugging Face repo id (e.g. \"Qwen/Qwen3-8B\"), read live from its config.json.","maxLength":200,"minLength":1,"type":"string"},"quant":{"default":"q4","description":"Weight quantisation: fp16 (FP16 / BF16), q8 (Q8_0), q6 (Q6_K), q5 (Q5_K_M), q4 (Q4_K_M), q3 (Q3_K_M). q4 is the common default.","enum":["fp16","q8","q6","q5","q4","q3"],"type":"string"},"vram_gb":{"description":"Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.","exclusiveMinimum":0,"maximum":4096,"type":"number"}},"type":"object"},"name":"can_i_run"},{"description":"Reads any Hugging Face model repo's config.json and parameter count and estimates its memory: the attention layout found (standard, sliding-window, hybrid or latent), how much each 1,000 tokens of context costs, and weights + KV cache + overhead at every quantisation. For models nodegrove.io has not reviewed; anything the reader cannot model is listed in warnings.","inputSchema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"active_params_b":{"description":"Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.","exclusiveMinimum":0,"maximum":10000,"type":"number"},"context":{"default":8192,"description":"Tokens held in context: prompt plus conversation.","maximum":10000000,"minimum":1,"type":"integer"},"kv_cache":{"default":"fp16","description":"KV cache precision. fp16 is what most runtimes use; q8 halves the cache.","enum":["fp16","q8"],"type":"string"},"repo":{"description":"Hugging Face repo id, e.g. \"Qwen/Qwen3-8B\", or its huggingface.co URL.","maxLength":200,"minLength":3,"type":"string"}},"required":["repo"],"type":"object"},"name":"estimate_from_hf_repo"},{"description":"How much memory an LLM needs: weights + KV cache + overhead at each quantisation (or one), at a given context, and the smallest common card class that holds each. Model: a name or id from list_models, any Hugging Face repo id, or its architecture (params_b, layers, kv_heads, head_dim).","inputSchema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"active_params_b":{"description":"Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.","exclusiveMinimum":0,"maximum":10000,"type":"number"},"architecture":{"description":"A model described by its config.json values instead of a name.","properties":{"active_params_b":{"description":"Parameters read per token, billions (mixture-of-experts only).","exclusiveMinimum":0,"maximum":10000,"type":"number"},"fixed_state_gb":{"description":"Fixed recurrent state of linear-attention or Mamba layers, GB.","maximum":100,"minimum":0,"type":"number"},"head_dim":{"description":"head_dim, or hidden_size ÷ num_attention_heads","exclusiveMinimum":0,"maximum":4096,"type":"integer"},"kv_groups":{"description":"Only for non-standard attention: one entry per group of layers that cache the same way. Replaces layers × kv_heads × head_dim.","items":{"properties":{"layers":{"exclusiveMinimum":0,"maximum":9007199254740991,"type":"integer"},"values_per_token":{"description":"Values each layer caches per token: 2 × KV heads × head dim, or the latent width for MLA.","exclusiveMinimum":0,"type":"number"},"window_tokens":{"description":"Sliding window: these layers keep only this many tokens.","exclusiveMinimum":0,"maximum":9007199254740991,"type":"integer"}},"required":["layers","values_per_token"],"type":"object"},"maxItems":8,"type":"array"},"kv_heads":{"description":"num_key_value_heads","exclusiveMinimum":0,"maximum":1024,"type":"integer"},"layers":{"description":"num_hidden_layers","exclusiveMinimum":0,"maximum":1000,"type":"integer"},"native_context":{"description":"The context window the model supports, tokens.","exclusiveMinimum":0,"maximum":9007199254740991,"type":"integer"},"params_b":{"description":"Total parameters, billions; all experts for a mixture-of-experts model.","exclusiveMinimum":0,"maximum":10000,"type":"number"}},"required":["params_b","layers","kv_heads","head_dim"],"type":"object"},"context":{"default":8192,"description":"Tokens held in context: prompt plus conversation.","maximum":10000000,"minimum":1,"type":"integer"},"kv_cache":{"default":"fp16","description":"KV cache precision. fp16 is what most runtimes use; q8 halves the cache.","enum":["fp16","q8"],"type":"string"},"model":{"description":"A model from list_models (id or name, e.g. \"llama-3.3-70b\" or \"Llama 3.3 70B\"), or any Hugging Face repo id (e.g. \"Qwen/Qwen3-8B\"), read live from its config.json.","maxLength":200,"minLength":1,"type":"string"},"quant":{"description":"Weight quantisation: fp16 (FP16 / BF16), q8 (Q8_0), q6 (Q6_K), q5 (Q5_K_M), q4 (Q4_K_M), q3 (Q3_K_M). Omit it for all 6.","enum":["fp16","q8","q6","q5","q4","q3"],"type":"string"}},"type":"object"},"name":"estimate_vram"},{"description":"The GPUs and machines nodegrove.io covers: memory, the memory a runtime can use and bandwidth, from the makers' specs, with each one's page.","inputSchema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"search":{"description":"Words to filter by, e.g. \"qwen\" or \"24 GB\".","maxLength":100,"type":"string"}},"type":"object"},"name":"list_gpus"},{"description":"The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-16): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.","inputSchema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"search":{"description":"Words to filter by, e.g. \"qwen\" or \"24 GB\".","maxLength":100,"type":"string"}},"type":"object"},"name":"list_models"},{"description":"Which open-weight LLMs fit this GPU: every model in list_models checked at one quantisation and context, with a recommended everyday model (the biggest class that fits with room for context at conversational speed), the largest that fits, the best at Q8 and the first out of reach. GPU: a name or id from list_gpus, or vram_gb for any other card.","inputSchema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"apple_silicon":{"description":"vram_gb is Apple unified memory; the GPU can use about 75% of it by default.","type":"boolean"},"bandwidth_gb_s":{"description":"Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.","exclusiveMinimum":0,"maximum":100000,"type":"number"},"context":{"default":8192,"description":"Tokens held in context: prompt plus conversation.","maximum":10000000,"minimum":1,"type":"integer"},"gpu":{"description":"A GPU from list_gpus (id or name, e.g. \"rtx-4090\", \"4090\" or \"M4 Max\").","maxLength":100,"minLength":1,"type":"string"},"quant":{"default":"q4","description":"Weight quantisation: fp16 (FP16 / BF16), q8 (Q8_0), q6 (Q6_K), q5 (Q5_K_M), q4 (Q4_K_M), q3 (Q3_K_M). q4 is the common default.","enum":["fp16","q8","q6","q5","q4","q3"],"type":"string"},"vram_gb":{"description":"Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.","exclusiveMinimum":0,"maximum":4096,"type":"number"}},"type":"object"},"name":"what_fits"}]},"body_sha256":"33c9184129ea59857336c6e18ddd7c4c92b8fc4440aa0947dd190b7c93729f2f","prev_id":null,"leaf":"0x60d4d513f06cacf9f9bedc1fe2f64209e579c33b676c7a24e7d00fe8f52219ab","leaf_text":"{\"body\":\"33c9184129ea59857336c6e18ddd7c4c92b8fc4440aa0947dd190b7c93729f2f\",\"id\":296801,\"kind\":\"mcp.tools\",\"method\":\"probe.mcp/1\",\"observed_us\":1793051998806923,\"prev\":null,\"subject\":\"51f8265d-c798-400d-9016-1abaccd9eb86\",\"subject_kind\":\"endpoint\"}","day":{"day":"2026-10-26","leaves":296695,"root":"0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8","chained":"0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a","anchor_chain":"eip155:5042002","anchor_tx":"0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae","anchor_block":69251483},"proof":["0x60d4b7a2a5f7b0458567c3e0f6c973181fb22f2b13d69d0b62d4ee442064812c","0xe118f931164f09dfcdd09ce18fba04151b15c7772c4c14e24d5c85bce42b4934","0x495f428ce4519bd5d06151298cc2faef9ffa0864e1767f5151d6b81bd86ee269","0x2bc605c6bbb40804a31eb027203bdc75b808b91c88810a79a048b8d52daac64e","0x5e018a4d6c960807a62209c9c9baa3adfe5d4a18a190f9546f078b63ebd06b0e","0x491ccd4b3e03a2ac8da2a20fffa689e9c6166b6c482cb398886c4e64c40c7f1b","0x7d3c9237eb8bf4e4b82d1392688dda8c8ae4dc70d79b2c45ec39d44546409d25","0x850bf292a1aa658b60949676a4a33cd2059a07cb0c90b415c8839258d415bdfb","0x8c6903777b1654f5fb12e259fed8098cda16e3130625244795d81936ec868a9c","0x490868b60140fda9b3c25d79c99d6f0d78d632ecde384aa788c6d47760ca6caa","0x52877ea072e10a1d3a921f7b54362005ad7a9baf5c99f31ec73a534bfea8930d","0xf4e3bedc99674db9d8ab4bc7655992ec76f822b327e6c89599b0baa3756fbd19","0x89fcaf55e37dd777228f271b79ea895534a66ec0d184363c2a6eb1b4d23c9ef1","0x216cebb9ae5414599109a02297c4817d7d1c6b1394afeb97efe38e32f0053974","0x7726154b91b2ad65b13849ef6cb6443b1f0ff113a3089c9bd5f2bcfc16be099d","0x47b89901b0f07938a6b9a66ddf35683903f79d756a7c7763665fd632758b08d0","0x9a83be955a206deb65b995adfd92c58fa31c95fbbf926bd199d300e70b08b26d","0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d","0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a"]}