Skip to content

fix(catalog): repoint three model rows at URLs that resolve #15

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Siddhesh2377 merged 9 commits into from
Aug 20, 2026
Merged

fix(catalog): repoint three model rows at URLs that resolve #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
456f79c
docs: rewrite the README as a consumer page and move build detail to …
Siddhesh2377 Aug 18, 2026
590363d
fix(catalog): point Qwen3.5 0.8B at a URL that resolves and correct i…
Siddhesh2377 Aug 20, 2026
7dd4115
fix(catalog): repoint Qwen3.8 27B and Gemma 4 E4B vision at URLs that…
Siddhesh2377 Aug 20, 2026
14195e1
feat(catalog): drop superseded families and add the verified current …
Siddhesh2377 Aug 20, 2026
8c9bd52
feat(models): file Granite, Maple, Muse and Fara under their real pub…
Siddhesh2377 Aug 20, 2026
eb916bf
Merge branch 'siddhesh/model-picker' into siddhesh/model-catalog
Siddhesh2377 Aug 20, 2026
004ae82
feat(models): file Ministral under Mistral and GLM under Zhipu AI
Siddhesh2377 Aug 20, 2026
b531012
docs: describe the current model picker and drop the model names that…
Siddhesh2377 Aug 20, 2026
3a5fdd8
Merge branch 'docs/readme-consumer-rewrite' into siddhesh/model-catalog
Siddhesh2377 Aug 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
357 changes: 103 additions & 254 deletions README.md
View file
Open in desktop

Large diffs are not rendered by default.

249 changes: 70 additions & 179 deletions app/src/main/java/com/runanywhere/runanywhereai/data/ModelCatalog.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,74 +207,14 @@ internal object ModelCatalog {

// --- LLM (llama.cpp) ------------------------------------------------------
private val llm = listOf(
// SmolLM2
SingleFileModel(
"smollm2-360m-q8_0",
"SmolLM2 360M Q8_0",
"https://huggingface.co/prithivMLmods/SmolLM2-360M-GGUF/resolve/main/SmolLM2-360M.Q8_0.gguf",
LLAMA,
LANGUAGE,
386_404_416
),
// Qwen (2.5, then 3, then 3.5)
SingleFileModel(
"qwen2.5-0.5b-instruct-q6_k",
"Qwen 2.5 0.5B Instruct Q6_K",
"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF/resolve/main/qwen2.5-0.5b-instruct-q6_k.gguf",
LLAMA,
LANGUAGE,
// downloadBytes defaults to memoryBytes, so a RAM-shaped round number here is also
// published as the transfer total the progress bar divides by. 600_000_000 is 50 MB short
// of the real asset (measured twice: 650_379_104 bytes on disk, and the HTTP layer logs
// `bytes_written=650379104`), which drove the bar to 100% at 92% of the file and left the
// line reading "596.2 MB of 572.2 MB" with the ETA gone while 50 MB was still arriving.
memoryBytes = 600_000_000,
downloadBytes = 650_379_104,
supportsLora = true
),
SingleFileModel(
"qwen2.5-1.5b-instruct-q4_k_m",
"Qwen 2.5 1.5B Instruct Q4_K_M",
"https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GGUF/resolve/main/qwen2.5-1.5b-instruct-q4_k_m.gguf",
LLAMA,
LANGUAGE,
2_500_000_000
),
SingleFileModel(
"qwen3-0.6b-q4_k_m",
"Qwen3 0.6B Q4_K_M",
"https://huggingface.co/unsloth/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
memoryBytes = 500_000_000,
downloadBytes = 396_705_472,
supportsThinking = true
),
SingleFileModel(
"qwen3-1.7b-q4_k_m",
"Qwen3 1.7B Q4_K_M",
"https://huggingface.co/unsloth/Qwen3-1.7B-GGUF/resolve/main/Qwen3-1.7B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
1_200_000_000,
supportsThinking = true
),
SingleFileModel(
"qwen3-4b-q4_k_m",
"Qwen3 4B Q4_K_M",
"https://huggingface.co/unsloth/Qwen3-4B-GGUF/resolve/main/Qwen3-4B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
2_800_000_000,
supportsThinking = true
),
SingleFileModel(
"qwen3.5-0.8b-q4_k_m",
"Qwen3.5 0.8B Q4_K_M",
"https://huggingface.co/bartowski/Qwen_Qwen3.5-0.8B-GGUF/resolve/main/Qwen3.5-0.8B-Q4_K_M.gguf",
"https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF/resolve/main/Qwen3.5-0.8B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
620_000_000,
memoryBytes = 900_000_000,
downloadBytes = 532_517_120,
supportsThinking = true
),
// Qwen3.6 — MoE (35B total / 3B active), agentic-coding-focused release.
Expand All @@ -293,10 +233,11 @@ internal object ModelCatalog {
SingleFileModel(
"qwen3.8-27b-q4_k_m",
"Qwen3.8 27B Q4_K_M (heavy)",
"https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-Q4_K_M.gguf",
"https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
17_106_775_008,
memoryBytes = 17_106_775_008,
downloadBytes = 16_464_440_224,
supportsThinking = true
),
// LFM2 / LFM2.5 (Liquid AI)
Expand All @@ -315,28 +256,6 @@ internal object ModelCatalog {
// 153,406,304 B of weights plus KV cache and runtime overhead.
190_000_000
),
// ONE quantization per model. The Q8_0 sibling of this row was removed
// deliberately: two quants of the same 350M model differ only in bytes
// (229 MB vs 379 MB), so the second row costs a catalog slot and a
// "which one do I pick?" decision without adding a capability. The same
// collapse was applied to LFM2 1.2B Tool and LFM2.5 2.6B below.
SingleFileModel(
"lfm2-350m-q4_k_m",
"LiquidAI LFM2 350M Q4_K_M",
"https://huggingface.co/LiquidAI/LFM2-350M-GGUF/resolve/main/LFM2-350M-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
250_000_000
),
// Q8_0 sibling removed — one quantization per model (see the 350M note above).
SingleFileModel(
"lfm2-1.2b-tool-q4_k_m",
"LiquidAI LFM2 1.2B Tool Q4_K_M",
"https://huggingface.co/LiquidAI/LFM2-1.2B-Tool-GGUF/resolve/main/LFM2-1.2B-Tool-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
800_000_000
),
SingleFileModel(
"lfm2.5-1.2b-instruct-q4_k_m",
"LiquidAI LFM2.5 1.2B Instruct Q4_K_M",
Expand All @@ -355,24 +274,6 @@ internal object ModelCatalog {
1_674_000_000,
supportsThinking = true
),
// Llama
SingleFileModel(
"llama-2-7b-chat-q4_k_m",
"Llama 2 7B Chat Q4_K_M",
"https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_K_M.gguf",
LLAMA,
LANGUAGE,
4_000_000_000
),
// Mistral
SingleFileModel(
"mistral-7b-instruct-q4_k_m",
"Mistral 7B Instruct Q4_K_M",
"https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf",
LLAMA,
LANGUAGE,
4_000_000_000
),
// Gemma
// Gemma 4 license: Google's Gemma Terms of Use (https://ai.google.dev/gemma/terms),
// not Apache — same license family as the gemma3n/gemma4 QHexRT rows in npuCatalog
Expand Down Expand Up @@ -429,14 +330,6 @@ internal object ModelCatalog {
LANGUAGE,
18_323_733_440
),
SingleFileModel(
"gemma-4-31b-it-ud-q2_k_xl",
"Gemma 4 31B IT UD-Q2_K_XL (heavy)",
"https://huggingface.co/unsloth/gemma-4-31B-it-GGUF/resolve/main/gemma-4-31B-it-UD-Q2_K_XL.gguf",
LLAMA,
LANGUAGE,
11_774_991_296
),
// Granite (IBM)
// Apache 2.0 (verified via HF cardData.license). Dense, three sizes.
SingleFileModel(
Expand Down Expand Up @@ -469,29 +362,6 @@ internal object ModelCatalog {
// Exact P0 NVIDIA checkpoint. The pinned llama.cpp fork has native
// `nemotron` support; this exact Q4_K_M artifact was load/inference
// checked through rcli on macOS before being exposed in the catalog.
SingleFileModel(
"nemotron-mini-4b-instruct-q4_k_m",
"NVIDIA Nemotron Mini 4B Instruct Q4_K_M",
"https://huggingface.co/bartowski/Nemotron-Mini-4B-Instruct-GGUF/resolve/fb49cde090c86092d89905bea2ffc41c23c2615e/Nemotron-Mini-4B-Instruct-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
2_697_387_072,
contextLength = 4_096
),
// Exact P0 NVIDIA Nano checkpoint. The file itself is 4.92 GB, while
// llama.cpp also needs KV/cache/compute headroom. Keep those two facts
// separate so the download planner validates the exact transport size
// and the mandatory SDK compatibility preflight requires 6 GiB of
// currently available RAM before either download or lifecycle load.
//
// INTENTIONAL CROSS-SDK DIVERGENCE: this row is Android/rcli-only. The
// pinned llama.cpp fork's `nemotron` path was load/inference checked for
// this exact Q4_K_M artifact through rcli on macOS (not yet an on-device
// Android smoke). iOS deliberately withholds it (ModelCatalogBootstrap:
// pending an Apple-provider inference smoke) and the Web catalog omits it
// (its ~4.92 GB single artifact exceeds the browser WASM32 4 GiB gate).
// Hold or re-scope this row if the Android llama.cpp path has to clear the
// same on-device bar iOS requires.
SingleFileModel(
"llama-3.1-nemotron-nano-4b-v1.1-q4_k_m",
"NVIDIA Llama 3.1 Nemotron Nano 4B v1.1 Q4_K_M",
Expand All @@ -512,6 +382,15 @@ internal object ModelCatalog {
downloadBytes = 4_920_736_864L,
contextLength = 4_096,
),
SingleFileModel(
"nemotron-mini-4b-instruct-q4_k_m",
"NVIDIA Nemotron Mini 4B Instruct Q4_K_M",
"https://huggingface.co/bartowski/Nemotron-Mini-4B-Instruct-GGUF/resolve/fb49cde090c86092d89905bea2ffc41c23c2615e/Nemotron-Mini-4B-Instruct-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
2_697_387_072,
contextLength = 4_096
),
// Bonsai (PrismML)
// Bonsai family at TRUE 1-bit (Q1_0, ~1.125 bit/wt) on CPU via llama.cpp — the same GGUF
// that runs on the NPU (bonsai_{4b,8b,27b}_1bit, QHEXRT). Requires a llama.cpp build with
Expand Down Expand Up @@ -562,6 +441,58 @@ internal object ModelCatalog {
// "invalid ggml type 142" — it only added Q1_0 (plain Bonsai) support, not
// Ternary-Bonsai's tensor encoding. Re-enable once the fork adds it.
// Ternary-Bonsai MLX works fine (iOS/macOS only — no MLX on Android).

// Added from the verified model list.
SingleFileModel(
"lfm2.5-1.2b-thinking-q4_k_m",
"LFM2.5 1.2B Thinking Q4_K_M",
"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
memoryBytes = 900_000_000,
downloadBytes = 730_895_360,
supportsThinking = true
),
SingleFileModel(
"qwen3.5-2b-q4_k_m",
"Qwen3.5 2B Q4_K_M",
"https://huggingface.co/unsloth/Qwen3.5-2B-GGUF/resolve/main/Qwen3.5-2B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
memoryBytes = 1_550_000_000,
downloadBytes = 1_280_835_840,
supportsThinking = true
),
SingleFileModel(
"qwen3.5-4b-q4_k_m",
"Qwen3.5 4B Q4_K_M",
"https://huggingface.co/unsloth/Qwen3.5-4B-GGUF/resolve/main/Qwen3.5-4B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
memoryBytes = 3_350_000_000,
downloadBytes = 2_740_937_888,
supportsThinking = true
),
SingleFileModel(
"qwen3.5-9b-q4_k_m",
"Qwen3.5 9B Q4_K_M",
"https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/resolve/main/Qwen3.5-9B-Q4_K_M.gguf",
LLAMA,
LANGUAGE,
memoryBytes = 6_950_000_000,
downloadBytes = 5_680_522_464,
supportsThinking = true
),
SingleFileModel(
"maple-preview-tq1_0",
"Maple Preview 20B-A1B TQ1_0 (1-bit)",
"https://huggingface.co/deepgrove/maple-preview-GGUF/resolve/main/maple-preview-TQ1_0-head-Q4_K.gguf",
LLAMA,
LANGUAGE,
memoryBytes = 6_100_000_000,
downloadBytes = 4_984_016_416,
supportsThinking = true
),
)

// --- VLM (llama.cpp, multimodal) ------------------------------------------
Expand Down Expand Up @@ -603,47 +534,6 @@ internal object ModelCatalog {
TAR_GZ,
ArchiveStructure.ARCHIVE_STRUCTURE_DIRECTORY_BASED
),
// Qwen (2-VL, then 2.5-VL)
MultiFileModel(
"qwen2-vl-2b-instruct-q4_k_m", "Qwen2-VL 2B Instruct", LLAMA, MULTIMODAL, 1_800_000_000,
files = listOf(
ModelFile(
"https://huggingface.co/ggml-org/Qwen2-VL-2B-Instruct-GGUF/resolve/main/Qwen2-VL-2B-Instruct-Q4_K_M.gguf",
"Qwen2-VL-2B-Instruct-Q4_K_M.gguf"
),
ModelFile(
"https://huggingface.co/ggml-org/Qwen2-VL-2B-Instruct-GGUF/resolve/main/mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf",
"mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf"
),
),
),
MultiFileModel(
"qwen2.5-vl-3b-instruct-q4_k_m", "Qwen2.5-VL 3B Instruct Q4_K_M", LLAMA, MULTIMODAL, 2_800_000_000,
files = listOf(
ModelFile(
"https://huggingface.co/ggml-org/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Q4_K_M.gguf",
"Qwen2.5-VL-3B-Instruct-Q4_K_M.gguf"
),
ModelFile(
"https://huggingface.co/ggml-org/Qwen2.5-VL-3B-Instruct-GGUF/resolve/main/mmproj-Qwen2.5-VL-3B-Instruct-Q8_0.gguf",
"mmproj-Qwen2.5-VL-3B-Instruct-Q8_0.gguf"
),
),
),
// LFM2-VL / LFM2.5-VL (Liquid AI)
MultiFileModel(
"lfm2-vl-450m-q8_0", "LFM2-VL 450M", LLAMA, MULTIMODAL, 600_000_000,
files = listOf(
ModelFile(
"https://huggingface.co/runanywhere/LFM2-VL-450M-GGUF/resolve/main/LFM2-VL-450M-Q8_0.gguf",
"LFM2-VL-450M-Q8_0.gguf"
),
ModelFile(
"https://huggingface.co/runanywhere/LFM2-VL-450M-GGUF/resolve/main/mmproj-LFM2-VL-450M-Q8_0.gguf",
"mmproj-LFM2-VL-450M-Q8_0.gguf"
),
),
),
// Q4_K_M, matching the Qwen2.5-VL 3B row beside it and the LFM2.5 2.6B LLM
// row this VLM is built on: one quantization per model, and Q4_K_M is what
// every other 3B-class GGUF row in this catalog ships. The mmproj is Q8_0
Expand Down Expand Up @@ -706,9 +596,10 @@ internal object ModelCatalog {
MultiFileModel(
"gemma-4-e4b-it-q4_k_m", "Gemma 4 E4B IT Q4_K_M (Experimental)", LLAMA, MULTIMODAL, 5_500_000_000,
files = listOf(
// ggml-org publishes no Q4_K_M for this repo — Q4_0 is its only 4-bit build.
ModelFile(
"https://huggingface.co/ggml-org/gemma-4-E4B-it-GGUF/resolve/main/gemma-4-E4B-it-Q4_K_M.gguf",
"gemma-4-E4B-it-Q4_K_M.gguf"
"https://huggingface.co/ggml-org/gemma-4-E4B-it-GGUF/resolve/main/gemma-4-E4B-it-Q4_0.gguf",
"gemma-4-E4B-it-Q4_0.gguf"
),
ModelFile(
"https://huggingface.co/ggml-org/gemma-4-E4B-it-GGUF/resolve/main/mmproj-gemma-4-E4B-it-Q8_0.gguf",
Expand Down
10 changes: 5 additions & 5 deletions app/src/main/java/com/runanywhere/runanywhereai/ui/screens/models/ModelRecommendation.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,12 +38,12 @@ object ModelRecommendation {
// Curated GGUF LLM ids, ordered best-first (product preference, not device fit).
private val preferredGgufLLMs: List<String> = listOf(
"lfm2.5-1.2b-instruct-q4_k_m",
"qwen3-1.7b-q4_k_m",
"lfm2-1.2b-tool-q4_k_m",
"qwen3-0.6b-q4_k_m",
"qwen2.5-0.5b-instruct-q6_k",
"lfm2-350m-q4_k_m",
"qwen3.5-2b-q4_k_m",
"lfm2.5-1.2b-thinking-q4_k_m",
"qwen3.5-0.8b-q4_k_m",
"granite-4.1-3b-q4_k_m",
"lfm2.5-230m-q4_k_m",
"bonsai-1.7b-q1_0",
)

// HNPU (QHexRT) LLMs surfaced first when the device reports a Hexagon NPU.
Expand Down
15 changes: 12 additions & 3 deletions app/src/main/java/com/runanywhere/runanywhereai/ui/screens/models/ModelTaxonomy.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,11 +15,14 @@ enum class ModelOrg(val brand: Brand) {
ALIBABA(RACBrands.Alibaba),
GOOGLE(RACBrands.Google),
MICROSOFT(RACBrands.Microsoft),
IBM(RACBrands.Ibm),
DEEPSEEK(RACBrands.DeepSeek),
LIQUID(RACBrands.Liquid),
MISTRAL(RACBrands.Mistral),
PRISM(RACBrands.Prism),
DEEPGROVE(RACBrands.Deepgrove),
OPENAI(RACBrands.OpenAI),
ZHIPU(RACBrands.Zhipu),
HUGGING_FACE(RACBrands.HuggingFace),
APPLE(RACBrands.Apple),
OPEN_SOURCE(RACBrands.OpenSource),
Expand Down Expand Up @@ -55,14 +58,20 @@ private val orgSpecs: List<OrgSpec> = listOf(
),
org(ModelOrg.DEEPSEEK, "deepseek"),
org(ModelOrg.PRISM, "bonsai"),
org(ModelOrg.MICROSOFT, "phi"),
org(ModelOrg.DEEPGROVE, "maple"),
org(ModelOrg.IBM, "granite"),
// "fara" sits with Microsoft's "phi" rather than on its own: Fara1.5 ships
// mirrored under our own HF org, so the catalog row names no publisher.
// Filing it by its own name beats guessing one into a UI label.
org(ModelOrg.MICROSOFT, "phi", "fara"),
org(ModelOrg.GOOGLE, "gemma", "embeddinggemma", "siglip"),
org(ModelOrg.META, "llama"),
org(ModelOrg.META, "llama", "muse-glimmer", "muse_glimmer"),
org(ModelOrg.ALIBABA, "qwen"),
org(ModelOrg.LIQUID, "lfm2"),
org(ModelOrg.MISTRAL, "mistral"),
org(ModelOrg.MISTRAL, "mistral", "ministral"),
org(ModelOrg.HUGGING_FACE, "smollm", "smolvlm"),
org(ModelOrg.OPENAI, "whisper"),
org(ModelOrg.ZHIPU, "glm"),
org(
ModelOrg.OPEN_SOURCE,
"internvl",
Expand Down
Loading