MarvinLabs vram_fit
REMOTE · MARVINLABS.ORG
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
Available components
Last scanned (5 hours ago)
Scores higher than 54% of remote servers
Reachable. Last reached 5 Nov 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability54
- AI-judged instruction clarity (fair).Partial
- Context-footprint check failed: tool/resource definitions use about 547 tokens (~182/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage82
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 46% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
- Stability: unverified → 0.03 ▲ functional
- 25 Oct 26 64
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://marvinlabs.org/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=marvinlabs.org | CN=WE1,O=Google Trust Services,C=US | 15 Oct 2026 | 13 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 9faf48094d83a67b0e0c5a7375aea14c |
| SANs: marvinlabs.org | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of marvinlabs.org. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| org. | present | 725, 26974 | 8, 8 | Verified |
| marvinlabs.org. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://marvinlabs.org/mcp | Verified | 200 | |
| http (plaintext) | http://marvinlabs.org/mcp | HTTPS enforced | 301 | https://marvinlabs.org/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
vram_fit ~201
Will this LoRA config train on a card with vram_gb GB? Returns verdict fits / tight / does_not_fit, the predicted peak in MB, the margin, how each part was derived, and any measured probe with the same settings.
| Name | Type | Req | Description |
|---|---|---|---|
| dora | boolean | – | – |
| lora_dropout | number | – | – |
| model | string | – | – |
| os | string | – | windows or linux; Windows spills instead of OOM |
| other_processes_mb | number | – | VRAM already held by other programs |
| quant | string | – | Base weights: bitsandbytes nf4 or bf16 |
| rank | integer | yes | – |
| response_len | integer | – | Tokens the loss covers (the response span) |
| seq_len | integer | – | Longest training example, in tokens |
| vram_gb | number | yes | Card memory as sold, in GB (8, 12, 16, 24...) |
No output schema declared.
No examples provided.
vram_max_rank ~172
Largest LoRA rank (multiple of 8) that fits with margin on a card with vram_gb GB, and the largest that is tight (a real run may fit, the one-step probe would not).
| Name | Type | Req | Description |
|---|---|---|---|
| dora | boolean | – | – |
| lora_dropout | number | – | – |
| model | string | – | – |
| other_processes_mb | number | – | VRAM already held by other programs |
| quant | string | – | Base weights: bitsandbytes nf4 or bf16 |
| response_len | integer | – | Tokens the loss covers (the response span) |
| seq_len | integer | – | Longest training example, in tokens |
| vram_gb | number | yes | Card memory as sold, in GB (8, 12, 16, 24...) |
No output schema declared.
No examples provided.
vram_probes ~103
The raw measured probe rows (RX 7900 XTX and RTX 3060 Ti), filtered by any of the given settings. gpu matches part of the card name, e.g. '7900' or '3060'.
| Name | Type | Req | Description |
|---|---|---|---|
| dora | boolean | – | – |
| gpu | string | – | – |
| lora_dropout | number | – | – |
| quant | string | – | – |
| rank | integer | – | – |
| seq_len | integer | – | – |
No output schema declared.
No examples provided.
How do I install the MarvinLabs vram_fit MCP server?
MarvinLabs vram_fit is a hosted endpoint at https://marvinlabs.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · marvinlabs.org
claude mcp add --transport http org-marvinlabs-vram-fit 'https://marvinlabs.org/mcp'
What is the MarvinLabs vram_fit MCP server?
MarvinLabs vram_fit is an MCP server listed in the public MCP registry as org.marvinlabs/vram-fit. Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes. This page covers its hosted endpoint (https://marvinlabs.org/mcp).
Is the MarvinLabs vram_fit MCP server safe to use?
MarvinLabs vram_fit scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the MarvinLabs vram_fit MCP server expose?
MarvinLabs vram_fit exposes 3 tools: vram_fit, vram_max_rank, vram_probes. Their descriptions and schemas cost roughly 476 tokens of context every time the server is loaded.
Does the MarvinLabs vram_fit MCP server require authentication?
No. We connected to MarvinLabs vram_fit without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the MarvinLabs vram_fit MCP server still maintained?
MarvinLabs vram_fit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.