minor8
kinggeezero基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 85001
minor9
kinggeezero基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DeepSeek-V4-Flash-180B-ROCmFP4-STRIX_LEAN-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DiffusionGemma-26B-A4B-it-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Gemma-4-26B-A4B-it-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Gemma-4-31B-it-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗GLM-4.7-Flash-ROCmFP4-STRIX-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF
kingjones777Four ROCmFP4/ROCmFPX tiers of `IFM/K2-Horizon-MoVA-36B-A4B`, quantised from the official BF16 GGUF and measured on a Ryzen AI Max+ 395 (Radeon 8060S, gfx1151, 128 GB unified, ROCm 7.2.4). This is the **dual-expert** `k2_horizon` MoVA architecture — 36B total parameters, **~4B active** — with two independent expert systems: a 64-way MoVA value-expert bank (top-4) alongside a 100-way MoE feed-forward (top-8), 48 layers, hidden 2560, and it is a **reasoning** model. **Every number on this card was measured on these exact files.** Nothing is estimated. As an A4B MoE, it decodes far faster than a dense 32B on the same hardware. **Start with `FAST`** — fastest on both axes here, all four answer correctly. Take `AGENT` only if you specifically want 8-bit weights.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗KAT-Coder-V2.5-Dev-Abliterated-MTP-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna-S-2.1-ROCmFP4-STRIX_LEAN-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Ling-3.0-flash-VL-MTP-ROCmFP4-GGUF
kingjones777`inclusionAI/Ling-3.0-flash-VL` (124B total / 5.5B active, native multimodal) quantized to ROCmFP4 for AMD Strix Halo, **with a multi-token-prediction head grafted in** from its text sibling — and with the server fix that lets **MTP and images work at the same time**, which they do not in stock llama.cpp. Everything below was measured on the shipped files on one Ryzen AI Max+ 395 (Radeon 8060S, 128 GiB unified). Numbers come from the built GGUFs and from server logs, never from estimates. ⚠️ **COHERENT is the worst of the three on this model** even though it is the largest and the highest bit-width (4.70 bpw vs 4.38). Its PPL is 0.80 worse than STRIX_LEAN — roughly 3.5σ against the ±0.23 error bars — and it is slower on both prefill and decode. It ships for completeness; it is not the "quality" option here. Tier ranking is model-dependent and has to be measured, not assumed.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniCPM-V-4.7-35B-A3B-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Mistral-Small-4-119B-ROCmFP4-GGUF
kingjones777> ### ⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL > 🚀 **37.86 tok/s** on a 119B MoE — **63.07 GiB**, 7 GiB smaller than UD-Q4_K_XL. A 4-bit **ROCmFP4** quantization for **AMD gfx1151 (Ryzen AI MAX+ 395 / Strix Halo)**, quantized from **BF16 (222 GiB)** — a lossless source, not a requantization of a lower-bit build. `Q4_0_ROCMFP4_COHERENT` (ftype 102) exists only in `charlie12345/ROCmFPX`, not upstream llama.cpp. Ignore the auto-generated "Use this model" commands above.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Muse-Glimmer-30B-ROCmFP4-Strix-Halo-DFlash-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Muse-Glimmer-30B-Uncensored-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Ornith-1.5-35B-A3B-Abliterated-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Ornith-1.5-35B-A3B-ROCmFP4-STRIX-LEAN-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Ornith-1.5-9B-Abliterated-ROCmFP4-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗OxCoder-9B-MTP-ROCmFP4-imatrix-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUF
kingjones777The ROCmFP4 files already in this repository (STRIX, STRIX_LEAN and FAST) are built without importance weighting. This file keeps the STRIX recipe but adds importance-matrix weighting from an agentic calibration imatrix, and raises the output head and the token embedding to Q6_K. The numbers below pair it with the DFlash2 draft head rather than the in-repo MTP head. **How it was built:** - Tool: `gufo-quant`, recipe STRIX, weighted with the agentic imatrix. - Tensor overrides: `output.weight` and `token_embd.weight` at Q6_K; census 866 tensors (82 at type 100, 421 at type 101). - The exact command line was not recorded. **Measured on Super ROC** (AMD Ryzen AI Max+ 395 (Radeon 8060S, gfx1151), 128 GB, ROCm 7.2.4; one request at a time, temperature 0, cold prompt cache):
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF
kingjones777Uncensored ROCmFP4 quantisations of Qwen/Qwen3.8-27B, built with the **same ROCmFPX pipeline and the same card ftypes** as `kingjones777/Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUF`. **Research artifact.** Abliteration removes content-refusal. It does not add capability. Do not ship this as a product default. The aligned repo remains the serving default. The aligned card's finding still stands: **the lever is MTP depth, not the ftype.** llama.cpp's default `--spec-draft-n-max 16` is about half the achievable throughput on this model. The knee is **n=4**. These uncensored files are the card's FAST (103) and STRIX_LEAN (106) from an abliterated BF16, plus Q6 AGENT/LEAN.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-Flash-Next-MTP-Heads-GGUF
kingjones777基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.