RapidChat 9B has 9.41 billion total parameters. The selected Q4_K_M GGUF file is 5.629 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
badr7
Total parameters
9,409,813,744
Exact file size
5,629,109,376 bytes
Quantization / precision
Q4_K_M
Weight repository
badr7/rapidchat-GGUF
Original model repository
badr7/rapidchat
Weight revision
890572eee51b281b7ed084e17d5d2855642c9742
Model revision
ec43f108da62669d650577e7f96d7a5ddf97fc1e
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-08
Date evidence
The merged BF16 RapidChat repository was created on 8 October 2026; its Apache-2.0 GGUF repository and selected Q4_K_M artifact followed on 9 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.
τ²-bench airline test · pass^1
82.5 / 100
Publisher pass^1 on the 20 official τ²-bench airline test-split tasks, four trials each, using a custom harness and an LLM user simulator. Specialist tool-use test; harness and simulator choices materially affect results.
Benchmark efficiency: 14.656 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: Publisher evaluation of the merged BF16 source checkpoint on the 20 official τ²-bench airline test-split tasks, four trials per task, without the optional working-notes file. The model was served with vLLM in BF16 at temperature 0.6, top_p 0.95 and top_k 20; the user simulator was gpt-6.1-sol with low reasoning, and the custom harness retained reasoning across tool calls with one retry after an empty reply.
Publisher-run source-checkpoint result, not an independent evaluation and not a benchmark of the selected Q4_K_M file. The publisher explicitly says its simulator and custom harness differ from the official frontier comparison. Thirty of the full suite's 50 airline tasks were seen during training, so only the separate 20-task test-split value is shown; failure analysis on official tasks also informed later synthetic scenarios. The Q4 repository's approximately 6-token/s smoke test omits the CPU model and other necessary conditions and is not presented as a speed result. The 5.629 GB file excludes runtime, KV cache and context memory and does not establish device compatibility.
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 5.629 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 5.63 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 5.629 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.