Nodegrove VRAM: can I run it?

Working · 2.3 s

io.nodegrove/vram-mcpv1.1.4 Domain verified

Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

Developer Tools

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://mcp.nodegrove.io/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

can_i_run Read-only

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.

gpustring

A GPU from list_gpus (id or name, e.g. "rtx-4090", "4090" or "M4 Max").

modelstring

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.

quantstring

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.

contextinteger

Tokens held in context: prompt plus conversation.

vram_gbnumber

Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.

kv_cachestring

KV cache precision. fp16 is what most runtimes use; q8 halves the cache.

architectureobject

A model described by its config.json values instead of a name.

apple_siliconboolean

vram_gb is Apple unified memory; the GPU can use about 75% of it by default.

bandwidth_gb_snumber

Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.

active_params_bnumber

Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.

Try it

Call this server's tools from your browser. Nothing to install.

https://mcp.nodegrove.io/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

can_i_run Read-only

gpustring

A GPU from list_gpus (id or name, e.g. "rtx-4090", "4090" or "M4 Max").

modelstring

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.

quantstring

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.

contextinteger

Tokens held in context: prompt plus conversation.

vram_gbnumber

Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.

kv_cachestring

KV cache precision. fp16 is what most runtimes use; q8 halves the cache.

architectureobject

A model described by its config.json values instead of a name.

apple_siliconboolean

vram_gb is Apple unified memory; the GPU can use about 75% of it by default.

bandwidth_gb_snumber

Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.

active_params_bnumber

Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.

Tools (6)

can_i_run

read-only

Argument	Type	Description
gpu	string	A GPU from list_gpus (id or name, e.g. "rtx-4090", "4090" or "M4 Max").
model	string	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.
quant	string	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.
context	integer	Tokens held in context: prompt plus conversation.
vram_gb	number	Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.
kv_cache	string	KV cache precision. fp16 is what most runtimes use; q8 halves the cache.
architecture	object	A model described by its config.json values instead of a name.
apple_silicon	boolean	vram_gb is Apple unified memory; the GPU can use about 75% of it by default.
bandwidth_gb_s	number	Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.
active_params_b	number	Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "gpu": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "A GPU from list_gpus (id or name, e.g. \"rtx-4090\", \"4090\" or \"M4 Max\")."
    },
    "model": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "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."
    },
    "quant": {
      "enum": [
        "fp16",
        "q8",
        "q6",
        "q5",
        "q4",
        "q3"
      ],
      "type": "string",
      "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."
    },
    "context": {
      "type": "integer",
      "default": 8192,
      "maximum": 10000000,
      "minimum": 1,
      "description": "Tokens held in context: prompt plus conversation."
    },
    "vram_gb": {
      "type": "number",
      "maximum": 4096,
      "description": "Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.",
      "exclusiveMinimum": 0
    },
    "kv_cache": {
      "enum": [
        "fp16",
        "q8"
      ],
      "type": "string",
      "default": "fp16",
      "description": "KV cache precision. fp16 is what most runtimes use; q8 halves the cache."
    },
    "architecture": {
      "type": "object",
      "required": [
        "params_b",
        "layers",
        "kv_heads",
        "head_dim"
      ],
      "properties": {
        "layers": {
          "type": "integer",
          "maximum": 1000,
          "description": "num_hidden_layers",
          "exclusiveMinimum": 0
        },
        "head_dim": {
          "type": "integer",
          "maximum": 4096,
          "description": "head_dim, or hidden_size ÷ num_attention_heads",
          "exclusiveMinimum": 0
        },
        "kv_heads": {
          "type": "integer",
          "maximum": 1024,
          "description": "num_key_value_heads",
          "exclusiveMinimum": 0
        },
        "params_b": {
          "type": "number",
          "maximum": 10000,
          "description": "Total parameters, billions; all experts for a mixture-of-experts model.",
          "exclusiveMinimum": 0
        },
        "kv_groups": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "layers",
              "values_per_token"
            ],
            "properties": {
              "layers": {
                "type": "integer",
                "maximum": 9007199254740991,
                "exclusiveMinimum": 0
              },
              "window_tokens": {
                "type": "integer",
                "maximum": 9007199254740991,
                "description": "Sliding window: these layers keep only this many tokens.",
                "exclusiveMinimum": 0
              },
              "values_per_token": {
                "type": "number",
                "description": "Values each layer caches per token: 2 × KV heads × head dim, or the latent width for MLA.",
                "exclusiveMinimum": 0
              }
            }
          },
          "maxItems": 8,
          "description": "Only for non-standard attention: one entry per group of layers that cache the same way. Replaces layers × kv_heads × head_dim."
        },
        "fixed_state_gb": {
          "type": "number",
          "maximum": 100,
          "minimum": 0,
          "description": "Fixed recurrent state of linear-attention or Mamba layers, GB."
        },
        "native_context": {
          "type": "integer",
          "maximum": 9007199254740991,
          "description": "The context window the model supports, tokens.",
          "exclusiveMinimum": 0
        },
        "active_params_b": {
          "type": "number",
          "maximum": 10000,
          "description": "Parameters read per token, billions (mixture-of-experts only).",
          "exclusiveMinimum": 0
        }
      },
      "description": "A model described by its config.json values instead of a name."
    },
    "apple_silicon": {
      "type": "boolean",
      "description": "vram_gb is Apple unified memory; the GPU can use about 75% of it by default."
    },
    "bandwidth_gb_s": {
      "type": "number",
      "maximum": 100000,
      "description": "Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.",
      "exclusiveMinimum": 0
    },
    "active_params_b": {
      "type": "number",
      "maximum": 10000,
      "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
    }
  }
}

estimate_from_hf_repo

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.

read-only

Argument	Type	Description
repo*	string	Hugging Face repo id, e.g. "Qwen/Qwen3-8B", or its huggingface.co URL.
context	integer	Tokens held in context: prompt plus conversation.
kv_cache	string	KV cache precision. fp16 is what most runtimes use; q8 halves the cache.
active_params_b	number	Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "repo"
  ],
  "properties": {
    "repo": {
      "type": "string",
      "maxLength": 200,
      "minLength": 3,
      "description": "Hugging Face repo id, e.g. \"Qwen/Qwen3-8B\", or its huggingface.co URL."
    },
    "context": {
      "type": "integer",
      "default": 8192,
      "maximum": 10000000,
      "minimum": 1,
      "description": "Tokens held in context: prompt plus conversation."
    },
    "kv_cache": {
      "enum": [
        "fp16",
        "q8"
      ],
      "type": "string",
      "default": "fp16",
      "description": "KV cache precision. fp16 is what most runtimes use; q8 halves the cache."
    },
    "active_params_b": {
      "type": "number",
      "maximum": 10000,
      "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
    }
  }
}

estimate_vram

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).

read-only

Argument	Type	Description
model	string	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.
quant	string	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.
context	integer	Tokens held in context: prompt plus conversation.
kv_cache	string	KV cache precision. fp16 is what most runtimes use; q8 halves the cache.
architecture	object	A model described by its config.json values instead of a name.
active_params_b	number	Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "model": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "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."
    },
    "quant": {
      "enum": [
        "fp16",
        "q8",
        "q6",
        "q5",
        "q4",
        "q3"
      ],
      "type": "string",
      "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."
    },
    "context": {
      "type": "integer",
      "default": 8192,
      "maximum": 10000000,
      "minimum": 1,
      "description": "Tokens held in context: prompt plus conversation."
    },
    "kv_cache": {
      "enum": [
        "fp16",
        "q8"
      ],
      "type": "string",
      "default": "fp16",
      "description": "KV cache precision. fp16 is what most runtimes use; q8 halves the cache."
    },
    "architecture": {
      "type": "object",
      "required": [
        "params_b",
        "layers",
        "kv_heads",
        "head_dim"
      ],
      "properties": {
        "layers": {
          "type": "integer",
          "maximum": 1000,
          "description": "num_hidden_layers",
          "exclusiveMinimum": 0
        },
        "head_dim": {
          "type": "integer",
          "maximum": 4096,
          "description": "head_dim, or hidden_size ÷ num_attention_heads",
          "exclusiveMinimum": 0
        },
        "kv_heads": {
          "type": "integer",
          "maximum": 1024,
          "description": "num_key_value_heads",
          "exclusiveMinimum": 0
        },
        "params_b": {
          "type": "number",
          "maximum": 10000,
          "description": "Total parameters, billions; all experts for a mixture-of-experts model.",
          "exclusiveMinimum": 0
        },
        "kv_groups": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "layers",
              "values_per_token"
            ],
            "properties": {
              "layers": {
                "type": "integer",
                "maximum": 9007199254740991,
                "exclusiveMinimum": 0
              },
              "window_tokens": {
                "type": "integer",
                "maximum": 9007199254740991,
                "description": "Sliding window: these layers keep only this many tokens.",
                "exclusiveMinimum": 0
              },
              "values_per_token": {
                "type": "number",
                "description": "Values each layer caches per token: 2 × KV heads × head dim, or the latent width for MLA.",
                "exclusiveMinimum": 0
              }
            }
          },
          "maxItems": 8,
          "description": "Only for non-standard attention: one entry per group of layers that cache the same way. Replaces layers × kv_heads × head_dim."
        },
        "fixed_state_gb": {
          "type": "number",
          "maximum": 100,
          "minimum": 0,
          "description": "Fixed recurrent state of linear-attention or Mamba layers, GB."
        },
        "native_context": {
          "type": "integer",
          "maximum": 9007199254740991,
          "description": "The context window the model supports, tokens.",
          "exclusiveMinimum": 0
        },
        "active_params_b": {
          "type": "number",
          "maximum": 10000,
          "description": "Parameters read per token, billions (mixture-of-experts only).",
          "exclusiveMinimum": 0
        }
      },
      "description": "A model described by its config.json values instead of a name."
    },
    "active_params_b": {
      "type": "number",
      "maximum": 10000,
      "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
    }
  }
}

list_gpus

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.

read-only

Argument	Type	Description
search	string	Words to filter by, e.g. "qwen" or "24 GB".

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "search": {
      "type": "string",
      "maxLength": 100,
      "description": "Words to filter by, e.g. \"qwen\" or \"24 GB\"."
    }
  }
}

list_models

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.

read-only

Argument	Type	Description
search	string	Words to filter by, e.g. "qwen" or "24 GB".

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "search": {
      "type": "string",
      "maxLength": 100,
      "description": "Words to filter by, e.g. \"qwen\" or \"24 GB\"."
    }
  }
}

what_fits

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.

read-only

Argument	Type	Description
gpu	string	A GPU from list_gpus (id or name, e.g. "rtx-4090", "4090" or "M4 Max").
quant	string	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.
context	integer	Tokens held in context: prompt plus conversation.
vram_gb	number	Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.
apple_silicon	boolean	vram_gb is Apple unified memory; the GPU can use about 75% of it by default.
bandwidth_gb_s	number	Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "gpu": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "A GPU from list_gpus (id or name, e.g. \"rtx-4090\", \"4090\" or \"M4 Max\")."
    },
    "quant": {
      "enum": [
        "fp16",
        "q8",
        "q6",
        "q5",
        "q4",
        "q3"
      ],
      "type": "string",
      "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."
    },
    "context": {
      "type": "integer",
      "default": 8192,
      "maximum": 10000000,
      "minimum": 1,
      "description": "Tokens held in context: prompt plus conversation."
    },
    "vram_gb": {
      "type": "number",
      "maximum": 4096,
      "description": "Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.",
      "exclusiveMinimum": 0
    },
    "apple_silicon": {
      "type": "boolean",
      "description": "vram_gb is Apple unified memory; the GPU can use about 75% of it by default."
    },
    "bandwidth_gb_s": {
      "type": "number",
      "maximum": 100000,
      "description": "Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.",
      "exclusiveMinimum": 0
    }
  }
}