Index Translate 2B has 2.274 billion total parameters. The selected Q4_K_M GGUF file is 1.312 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
Index Team
Total parameters
2,274,069,824
Exact file size
1,312,164,352 bytes
Quantization / precision
Q4_K_M
Weight repository
IndexTeam/Index-Translate-2B-GGUF
Original model repository
IndexTeam/Index-Translate-2B
Weight revision
449c9e6457b3632d328c6cbb78ae8e8e0c8059a5
Model revision
a516854233b170140b57d36b48d7148c0edebabb
Runtime notes
Translation specialist, not a general chat ranking. Apache-2.0 licensed. The official llama.cpp recipe uses the chat template with thinking disabled, temperature 0 and the target-language prompt. This 1.312 GB Q4_K_M file is text-capable by itself; image input needs the separate compatible projector. Runtime, KV cache and long contexts need memory beyond the weight file. The recorded FLORES result is from the source checkpoint, not a Q4 speed or compatibility test.
Recorded release date
2026-09-28
Date evidence
Official Index Team source checkpoint created 28 September 2026; official GGUF conversion published 3 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.
FLORES · COMET-22 (126k / 420)
86.55 / 100
Publisher-reported COMET-22 across 126,000 translation inputs and 420 directions among 21 languages. Displayed on a 0–100 scale; this is not a general intelligence or speed test.
Benchmark efficiency: 65.96 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: Index Team publisher evaluation on 126,000 FLORES inputs across 420 translation directions among 21 languages. Text translation used greedy decoding and a 16,384-token context window. The source reports COMET-22 0.8655; Local AI Stats displays the same value multiplied by 100.
Source-checkpoint result, not an independent test and not a direct benchmark of this Q4_K_M file. The official GGUF card reports A100 consistency checks against F16 and near-verbatim Q4_K_M greedy spot checks, but it does not publish this full FLORES score for the quantized file. File size excludes runtime, KV cache and the optional multimodal projector; it does not establish device speed or 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 1.312 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 1.31 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.
Translation specialist, not a general chat ranking. Apache-2.0 licensed. The official llama.cpp recipe uses the chat template with thinking disabled, temperature 0 and the target-language prompt. This 1.312 GB Q4_K_M file is text-capable by itself; image input needs the separate compatible projector. Runtime, KV cache and long contexts need memory beyond the weight file. The recorded FLORES result is from the source checkpoint, not a Q4 speed or compatibility test. The selected weights use 1.312 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.