SOLAR-10.7B-Instruct-v1.0 is a 10.7 billion parameter model that outperforms models with up to 30 billion parameters using a depth up-scaling methodology incorporating Mistral 7B weights.
The installation script explicitly requires the wasi_nn-ggml plugin to enable GGML inference capabilities.
The API server command uses the same GGUF file and port configuration as the direct chat application.
secondstate.io2024-01-031 HN pts628 words
Where to run it
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 29 quantized builds for local use; a big base for builders (228 fine-tunes, adapters and merges).
Everything else, folded: the full tables, every source.
Benchmarks
2 rows
Benchmarks 2 rows
measured third-party leaderboard rowauthor-reported number from the model card or eval files (2)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
SOLAR-10.7B-Instruct-v1.0 is a 10.7B parameter llama-based model fine-tuned for single-turn conversation.[1][2] The model uses a depth up-scaling methodology and is released under a CC BY-NC 4.0 license.[3][4]
Generated 2026-10-07 15:08 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Use-case evidence
2 use cases
What it is good at 2 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
License: CC BY-NC 4.0 (friction: non-commercial). Non-commercial only; commercial hosting not permitted without a separate license. (license file, observed 2026-10-24)
Hosted endpoints observed for SOLAR-10.7B-Instruct-v1.0, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
secondstate.io2024-01-03HN 1 pts · 0 comments628 words
SOLAR-10.7B-Instruct-v1.0 is a 10.7 billion parameter model that outperforms models with up to 30 billion parameters using a depth up-scaling methodology incorporating Mistral 7B weights. Engineers run the Q5_K_M.gguf file via WasmEdge on local devices, starting an API server at http://localhost:8080 without complex Python packages or C++ toolchains. The portable Wasm app automatically utilizes hardware accelerators like GPUs for inference.written, reviewed, cited
The installation script explicitly requires the wasi_nn-ggml plugin to enable GGML inference capabilities.
The API server command uses the same GGUF file and port configuration as the direct chat application.
Papers
3 papers
Papers 3
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
