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.
HumanEval
86 / 100
Writing short Python functions. Base HumanEval pass@1, separate from HumanEval+ and small subsets.
Benchmark efficiency: 14.462 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: Corrected 23 September 2026 full HumanEval-164 run: 141/164 pass, reported as 86.0%; greedy pass@1, thinking off.
Requires PrismML llama.cpp fork. Earlier results with insufficient context were withdrawn. This is the corrected publisher result; thinking mode has documented non-completion problems.
Zero-shot MMLU accuracy. Kept separate from mixed/few-shot published scores. Runtime, prompt formatting and weight precision can still differ.
Benchmark efficiency: 13.14 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: All 14,042 MMLU questions, zero-shot; publisher 23 September 2026 paired test of the shipped PTQ1_0 model; thinking off.
Requires PrismML llama.cpp fork. Publisher result, not independent reproduction. Thinking mode has documented non-completion problems; use thinking off.
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 5.947 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.
Need a computer for Ternary Bonsai 2 27B Abliterated (BoldingBuilds)?
These complete configurations pass the initial weight-size check for the selected 5.95 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 5.947 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.