The LPDDR5 memory is listed with a 16GB maximum; no RAM upgrade is assumed.
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.
Fixed 24GB memory and internal storage limit model size; no CUDA support; Amazon main-offer price and stock were not verified in this run.
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.
Memory is soldered and shared with the operating system.
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.
Weight size is not tested compatibility or speed. Check runtime support and memory for context before buying. Prices are dated references. As an Amazon Associate I earn from qualifying purchases.
How these options are selected
Up to three platforms, with the lowest dated reference price on each. Unknown prices follow known prices. Each memory pool keeps a reserve: 30% (minimum 2 GB) for system or unified memory; 20% (minimum 1 GB) for dedicated VRAM. System RAM is for CPU inference. This check does not establish GPU allocation, software support or context capacity.
Model file and details
Provider
webAI
Total parameters
8,791,592,960
Exact file size
5,347,917,248 bytes
Quantization / precision
Q4_K_M
Weight repository
webAI-Official/TwIL-8B
Original model repository
webAI-Official/TwIL-8B
Weight revision
58d49f0d9909e62f9c2fb09e99fc5c76f3f2d630
Model revision
58d49f0d9909e62f9c2fb09e99fc5c76f3f2d630
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-14
Date evidence
HF source repository creation date, not a verified public launch date. Current verbose artifact and variant-specific model-card scores reviewed on 6 November 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.
MMLU-Pro
76.5 / 100
Knowledge and reasoning across many subjects. Published accuracy; different evaluation settings can change the result.
Benchmark efficiency: 14.305 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 internal high-effort pass@1 with thinking enabled, verbose variant only (dagger rows on source card). LiveCodeBench version is not established for this model; the card identifies competitor results as v6 only.
Publisher-reported source-checkpoint result; not an independent test or a score measured on this Q4_K_M file. No confidence interval is supplied. Download bytes cover language weights, not total runtime memory. English reasoning model; 131,072-token context. webAI Non-Commercial License v1.0. Balanced and verbose use different checkpoints: scores must not be transferred between them. Exact decoding settings, harness revision and repeated-run counts are not disclosed.
Writing short Python functions. Base HumanEval pass@1, separate from HumanEval+ and small subsets.
Benchmark efficiency: 17.427 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 internal high-effort pass@1 with thinking enabled, verbose variant only (dagger rows on source card). LiveCodeBench version is not established for this model; the card identifies competitor results as v6 only.
Publisher-reported source-checkpoint result; not an independent test or a score measured on this Q4_K_M file. No confidence interval is supplied. Download bytes cover language weights, not total runtime memory. English reasoning model; 131,072-token context. webAI Non-Commercial License v1.0. Balanced and verbose use different checkpoints: scores must not be transferred between them. Exact decoding settings, harness revision and repeated-run counts are not disclosed.
Writing Python that passes extra edge-case tests. EvalPlus pass@1 on all 164 problems.
Benchmark efficiency: 16.511 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 internal high-effort pass@1 with thinking enabled, verbose variant only (dagger rows on source card). LiveCodeBench version is not established for this model; the card identifies competitor results as v6 only.
Publisher-reported source-checkpoint result; not an independent test or a score measured on this Q4_K_M file. No confidence interval is supplied. Download bytes cover language weights, not total runtime memory. English reasoning model; 131,072-token context. webAI Non-Commercial License v1.0. Balanced and verbose use different checkpoints: scores must not be transferred between them. Exact decoding settings, harness revision and repeated-run counts are not disclosed.
Basic Python programming with extra tests. EvalPlus pass@1 on the sanitized 378-problem set.
Benchmark efficiency: 14.791 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 internal high-effort pass@1 with thinking enabled, verbose variant only (dagger rows on source card). LiveCodeBench version is not established for this model; the card identifies competitor results as v6 only.
Publisher-reported source-checkpoint result; not an independent test or a score measured on this Q4_K_M file. No confidence interval is supplied. Download bytes cover language weights, not total runtime memory. English reasoning model; 131,072-token context. webAI Non-Commercial License v1.0. Balanced and verbose use different checkpoints: scores must not be transferred between them. Exact decoding settings, harness revision and repeated-run counts are not disclosed.
Published coding pass rates without a verified benchmark version. Do not compare these directly with the v6 view.
Benchmark efficiency: 15.258 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 internal high-effort pass@1 with thinking enabled, verbose variant only (dagger rows on source card). LiveCodeBench version is not established for this model; the card identifies competitor results as v6 only.
Publisher-reported source-checkpoint result; not an independent test or a score measured on this Q4_K_M file. No confidence interval is supplied. Download bytes cover language weights, not total runtime memory. English reasoning model; 131,072-token context. webAI Non-Commercial License v1.0. Balanced and verbose use different checkpoints: scores must not be transferred between them. Exact decoding settings, harness revision and repeated-run counts are not disclosed.
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 5.348 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.
Confirm model architecture and quantization support in your runner. The selected weights use 5.348 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.