ThakiCloud RAG-Gate-27B has 27.321 billion total parameters. The selected Q4_K_M GGUF file is 16.547 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
ThakiCloud
Total parameters
27,320,697,856
Exact file size
16,547,401,504 bytes
Quantization / precision
Q4_K_M
Weight repository
mradermacher/RAG-Gate-27B-GGUF
Original model repository
ThakiCloud/RAG-Gate-27B
Weight revision
848de16c1866e568b3317f18883acf41453b70e9
Model revision
3f008df4d711f1aca5014d6b5e59646a0eca9c7d
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-07
Date evidence
ThakiCloud published the merged BF16 RAG-Gate-27B checkpoint on 7 October 2026; this third-party static GGUF repository was created and completed on 8 October 2026.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
RAG-Gate · blind action accuracy
93.8 / 100
Accuracy choosing Answer, Retrieve or Stop on a publisher-held blind set of 14,818 evidence-state items from 2,256 multi-hop questions. Specialist evidence-sufficiency test, not a general intelligence benchmark.
Benchmark efficiency: 5.669 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: ThakiCloud publisher evaluation of the merged BF16 source checkpoint on a held-out test set of 14,818 evidence-state items covering 2,256 distinct MuSiQue-derived multi-hop questions. The model selects the first-token action Answer, Retrieve or Stop from label probabilities without sampling. The reported 95% confidence interval, bootstrapped over base questions with 10,000 resamples, is 93.2% to 94.4%.
Source-checkpoint result, not an independent evaluation and not a direct benchmark of the selected Q4_K_M file. The publisher reports 5.5% unsupported-answer and 7.1% over-refusal rates, but evaluation is English-only, in-domain, limited to one source domain and inputs up to 2,048 tokens. The 16.547 GB file excludes runtime, KV cache and context memory; it does not establish device compatibility or speed.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 16.547 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
These complete configurations pass the initial weight-size check for the selected 16.55 GB file. Allow extra memory for context and software. Check the model’s runtime notes and your inference software before buying.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Memory matches are estimates, not tested compatibility or speed. As an Amazon Associate I earn from qualifying purchases.
Confirm model architecture and quantization support in your runner. The selected weights use 16.547 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.