Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
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.
Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Estimates using curated, config-derived architecture fields (MLA, sliding-window, hybrid attention, MoE modeled).
LLM name, fuzzy — e.g. "GLM-4.7-Flash", "gpt-oss-20b", "gemma 31b"
Alias of context_tokens — accepted because the REST API uses this name. Do not pass both with different values.
Discrete-GPU OS reserve: windows-display (default, 2 GB/card) · linux-display (1.2 GB) · linux-headless (0.6 GB, a second card with no display). Not for Macs or DGX Spark-class systems.
GPU name, fuzzy — e.g. "RTX 4090", "RX 7900 XTX", "A100 80GB". Multi-GPU rigs: join with + — e.g. "RTX 5090 + RTX 3090" (VRAM pools across cards). Provide gpu OR mac_ram_gb.
Weight quantization. GPU: Q4_K_M(default)/Q5_K_M/Q6_K/Q8_0/FP16. Mac: 4/8(default)/16 (bits).
KV-cache quantization bits (default 16 = F16)
Number of identical copies of the gpu (e.g. gpu="RTX 3090", gpu_count=2 for a 2×3090 rig; gpu="DGX Spark 128GB", gpu_count=2 or 4 for linked units under vLLM+Ray or TensorRT-LLM). Default 1.
Apple Silicon unified memory in GB — e.g. 16, 64, 512. Provide gpu OR mac_ram_gb.
Context length in tokens (default 8192). Alias: ctx (same field as the REST API).
Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Estimates using curated, config-derived architecture fields (MLA, sliding-window, hybrid attention, MoE modeled).
| Argument | Type | Description |
|---|---|---|
| ctx | integer | Alias of context_tokens — accepted because the REST API uses this name. Do not pass both with different values. |
| env | string | Discrete-GPU OS reserve: windows-display (default, 2 GB/card) · linux-display (1.2 GB) · linux-headless (0.6 GB, a second card with no display). Not for Macs or DGX Spark-class systems. |
| gpu | string | GPU name, fuzzy — e.g. "RTX 4090", "RX 7900 XTX", "A100 80GB". Multi-GPU rigs: join with + — e.g. "RTX 5090 + RTX 3090" (VRAM pools across cards). Provide gpu OR mac_ram_gb. |
| model* | string | LLM name, fuzzy — e.g. "GLM-4.7-Flash", "gpt-oss-20b", "gemma 31b" |
| quant | string | Weight quantization. GPU: Q4_K_M(default)/Q5_K_M/Q6_K/Q8_0/FP16. Mac: 4/8(default)/16 (bits). |
| kv_bits | number | KV-cache quantization bits (default 16 = F16) |
| gpu_count | integer | Number of identical copies of the gpu (e.g. gpu="RTX 3090", gpu_count=2 for a 2×3090 rig; gpu="DGX Spark 128GB", gpu_count=2 or 4 for linked units under vLLM+Ray or TensorRT-LLM). Default 1. |
| mac_ram_gb | integer | Apple Silicon unified memory in GB — e.g. 16, 64, 512. Provide gpu OR mac_ram_gb. |
| context_tokens | integer | Context length in tokens (default 8192). Alias: ctx (same field as the REST API). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"model"
],
"properties": {
"ctx": {
"type": "integer",
"minimum": 1024,
"description": "Alias of context_tokens — accepted because the REST API uses this name. Do not pass both with different values."
},
"env": {
"enum": [
"linux-headless",
"linux-display",
"windows-display"
],
"type": "string",
"description": "Discrete-GPU OS reserve: windows-display (default, 2 GB/card) · linux-display (1.2 GB) · linux-headless (0.6 GB, a second card with no display). Not for Macs or DGX Spark-class systems."
},
"gpu": {
"type": "string",
"description": "GPU name, fuzzy — e.g. \"RTX 4090\", \"RX 7900 XTX\", \"A100 80GB\". Multi-GPU rigs: join with + — e.g. \"RTX 5090 + RTX 3090\" (VRAM pools across cards). Provide gpu OR mac_ram_gb."
},
"model": {
"type": "string",
"description": "LLM name, fuzzy — e.g. \"GLM-4.7-Flash\", \"gpt-oss-20b\", \"gemma 31b\""
},
"quant": {
"type": "string",
"description": "Weight quantization. GPU: Q4_K_M(default)/Q5_K_M/Q6_K/Q8_0/FP16. Mac: 4/8(default)/16 (bits)."
},
"kv_bits": {
"enum": [
16,
8,
4
],
"type": "number",
"description": "KV-cache quantization bits (default 16 = F16)"
},
"gpu_count": {
"type": "integer",
"maximum": 8,
"minimum": 1,
"description": "Number of identical copies of the gpu (e.g. gpu=\"RTX 3090\", gpu_count=2 for a 2×3090 rig; gpu=\"DGX Spark 128GB\", gpu_count=2 or 4 for linked units under vLLM+Ray or TensorRT-LLM). Default 1."
},
"mac_ram_gb": {
"type": "integer",
"maximum": 2048,
"minimum": 8,
"description": "Apple Silicon unified memory in GB — e.g. 16, 64, 512. Provide gpu OR mac_ram_gb."
},
"context_tokens": {
"type": "integer",
"minimum": 1024,
"description": "Context length in tokens (default 8192). Alias: ctx (same field as the REST API)."
}
},
"additionalProperties": false
}List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only HuggingFace transformer configs can also be checked via fitllm.run; unsupported architectures are rejected.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?", "best local model for my machine?", or gives hardware without naming a model.
| Argument | Type | Description |
|---|---|---|
| gpu | string | GPU name, fuzzy. Multi-GPU rigs: join with + (e.g. "RTX 5090 + RTX 3090"). Provide gpu OR mac_ram_gb. |
| gpu_count | integer | Number of identical copies of the gpu. Default 1. |
| mac_ram_gb | integer | Apple Silicon unified memory GB. Provide gpu OR mac_ram_gb. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"gpu": {
"type": "string",
"description": "GPU name, fuzzy. Multi-GPU rigs: join with + (e.g. \"RTX 5090 + RTX 3090\"). Provide gpu OR mac_ram_gb."
},
"gpu_count": {
"type": "integer",
"maximum": 8,
"minimum": 1,
"description": "Number of identical copies of the gpu. Default 1."
},
"mac_ram_gb": {
"type": "integer",
"maximum": 2048,
"minimum": 8,
"description": "Apple Silicon unified memory GB. Provide gpu OR mac_ram_gb."
}
},
"additionalProperties": false
}