Model: K2 Horizon 7B

MBZUAI's Institute of Foundation Models released K2 Horizon 7B, the small dense member of its K2 Horizon family, under Apache 2.0 with its training data. Despite the 7B name, the model holds 9.0B parameters because its 250K-token vocabulary input and output tables add about 2B, and it supports a 524K maximum context. IFM's own GGUF files put Q4_K_M at 5.59 GB (5,592,217,984 bytes) and Q8_0 at 9.57 GB (9,573,964,160 bytes), with the site estimating Q4_K_M at about 6.5 GB of VRAM at 4K context, comfortable on an 8 GB card, while 128K context needs about 25.6 GB; llama.cpp runs it as `k2-horizon`.

K2 Horizon 7B 7B MBZUAI K2 Horizon The small dense member of MBZUAI IFM's K2 Horizon family, Apache 2.0, released with its training data. It is called 7B but holds 9.0B parameters: the 250K-token vocabulary's input and output tables add about 2B. Q4 K M is about 6.5 GB at 4K, comfortable on an 8 GB card at that length; a 16 GB card holds it comfortably to 32K 10.8 GB , and 128K needs about 25.6 GB because every layer keeps an ordinary KV cache. llama.cpp runs it as k2-horizon . Sizes come from IFM's own GGUF files bartowski's Q4 K M is about 0.2 GB larger ; no per-level quality loss has been published. 524K Max Context 4 Quant Variants GGUF Q8 0 Best Quality — Accuracy Retained Quantization Variants Per-quant VRAM, quality loss, and inference speed on RTX 4090 Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports | Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions | |---|---|---|---|---|---|---|---| | GGUF | Q4 K M | 4.97 | 6.5 GB | — | — | Estimated | | | GGUF | Q5 K M | 5.74 | 7.4 GB | — | — | Estimated | | | GGUF | Q6 K | 6.57 | 8.3 GB | — | — | Estimated | | | GGUF | Q8 0 | 8.5 | 10.6 GB | — | — | Estimated | | Which file each size is for A file size is not a memory figure: the VRAM column adds the KV cache at 4K context and runtime buffers to the weights. A vision projector mmproj , where the repo ships one, is a separate download and is in neither number. - GGUF Q4 K M IFM/K2-Horizon-7B-GGUF https://huggingface.co/IFM/K2-Horizon-7B-GGUF · K2-Horizon-7B-Q4 K M.gguf · 5.59 GB 5,592,217,984 bytes · listing read 2026-10-21 - GGUF Q5 K M IFM/K2-Horizon-7B-GGUF https://huggingface.co/IFM/K2-Horizon-7B-GGUF · K2-Horizon-7B-Q5 K M.gguf · 6.47 GB 6,466,075,008 bytes · listing read 2026-10-21 - GGUF Q6 K IFM/K2-Horizon-7B-GGUF https://huggingface.co/IFM/K2-Horizon-7B-GGUF · K2-Horizon-7B-Q6 K.gguf · 7.39 GB 7,394,548,096 bytes · listing read 2026-10-21 - GGUF Q8 0 IFM/K2-Horizon-7B-GGUF https://huggingface.co/IFM/K2-Horizon-7B-GGUF · K2-Horizon-7B-Q8 0.gguf · 9.57 GB 9,573,964,160 bytes · listing read 2026-10-21 Similar models Compare with K2 Horizon https://quantized.uk/tools/compare/?a=k2-horizon-7b&b=k2-horizon-mova-36b-a4b 36B-A4BConsumer GPUPro GPU24.2 GBmin VRAM—accuracy https://quantized.uk/quant-hub/k2-horizon-mova-36b-a4b/ K2 Horizon MoVA 36B-A4B MBZUAI K2 Horizon The mixture-of-experts member of MBZUAI IFM's K2 Horizon family: 37.5B parameters with about 4B active per token, Apache 2.0, released with its training data. Every one of its 48 layers keeps an ordinary KV cache, so context is not cheap: Q4 K M is about 24.2 GB at 4K, which is tight on a 24 GB card, and comfortable on a 32 GB card up to 16K. The 512K window would need about 129 GB. llama.cpp runs it as k2-horizon . Sizes come from IFM's own GGUF files bartowski's Q4 K M is about 0.3 GB larger ; no per-level quality loss has been published. 32BConsumer GPUPro GPU23.1 GBmin VRAM—accuracy https://quantized.uk/quant-hub/k2-horizon-32b/ K2 Horizon 32B MBZUAI K2 Horizon The dense 32B member of MBZUAI IFM's K2 Horizon family 34.8B counted, Apache 2.0, released with its training data . All 64 layers keep an ordinary KV cache with 8 KV heads: Q4 K M is about 23.1 GB at 4K, tight on a 24 GB card and comfortable on a 32 GB card up to 16K; each extra 32K of context adds roughly 8.8 GB. llama.cpp runs it as k2-horizon . Sizes come from IFM's own GGUF files bartowski's Q4 K M is about 1 GB larger ; no per-level quality loss has been published. 8BConsumer GPUMac / Apple Silicon5.3 GBmin VRAM99.7%accuracy https://quantized.uk/quant-hub/qwen3-vl-8b/ Qwen3-VL 8B Instruct Alibaba Qwen3-VL Current-generation vision-language model that still fits a single 8–12GB card at Q4 ~5.9GB . The realistic multimodal option for people without a 24GB GPU — note the vision encoder adds VRAM the KV-cache math below does not model. 9BConsumer GPUMac / Apple Silicon6.6 GBmin VRAM—accuracy https://quantized.uk/quant-hub/qwen3-5-9b/ Qwen3.5 9B Alibaba Qwen3.5 The newest small Qwen and a common pick for 8 to 16 GB cards. Only 8 of its 32 layers keep a growing KV cache, so it can use a long context on modest hardware. At Q4 K M it needs about 6.6 GB at 4K and 7.0 GB at 16K, comfortable on an 8 GB card; at 32K 7.5 GB it is tight there and comfortable from 10 GB up. Its full 256K window needs about 15.2 GB. Q8 0 needs about 10.4 GB, comfortable from 12 GB up. Reasoning is off by default on the small Qwen3.5 sizes, and it reads images through a separate vision encoder. Sizes come from the published GGUF file sizes, and no per-level quality loss has been published. Running K2 Horizon 7B locally At Q4 K M and 4K of context, K2 Horizon 7B needs about 6.5 GB — 5.3 GB of weights, 0.56 GB of KV cache and a 0.6 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 9 of them, from the RTX 4060 up — and 76 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs. What longer context costs Going from 4K to 32K adds about 3.94 GB, taking the total to 10.8 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 512K; holding all of it at Q4 K M would need about 85 GB. Which build to download This index only tracks K2 Horizon 7B in GGUF, across 4 levels Q4 K M, Q5 K M, Q6 K, Q8 0 . No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving. Common questions - How much VRAM does K2 Horizon 7B need? - About 6.5 GB at Q4 K M with 4K of context and batch 1, rising to roughly 10.8 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card. - Will K2 Horizon 7B run on a 8GB GPU? - Yes — at Q4 K M and 4K context it needs about 6.5 GB, which leaves 1.5 GB spare on a RTX 4060, or on any of the other 8 GB cards here 9 in all . That is the smallest size in this index that clears it comfortably; 76 of 78 do. - Which quantization of K2 Horizon 7B should I use? - No published quality comparison exists for this model, so pick by footprint: Q4 K M is the level most people run, and a higher bits-per-weight level is more faithful. All 4 levels in the index are Q4 K M, Q5 K M, Q6 K, Q8 0. Where this model fits Sized at Q4 K M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory. - Runs comfortably on - RTX 40608GB · +1.5 https://quantized.uk/gpu/rtx-4060/ RTX 4060 Ti 8G8GB · +1.5 https://quantized.uk/gpu/rtx-4060-ti-8g/ Radeon RX 9060 XT 8G8GB · +1.5 https://quantized.uk/gpu/radeon-rx-9060-xt-8g/ RTX 5060 Ti 8G8GB · +1.5 https://quantized.uk/gpu/rtx-5060-ti-8g/ RTX 50608GB · +1.5 https://quantized.uk/gpu/rtx-5060/ - Just misses - Mac M1 8G+0.5GB over https://quantized.uk/gpu/mac-m1-8g/ Mac M3 8G+0.5GB over https://quantized.uk/gpu/mac-m3-8g/ - Ships in - GGUF https://quantized.uk/formats/gguf/ - Try it yourself - Size it in the calculator https://quantized.uk/tools/vram-calc/?model=k2-horizon-7b&quant=Q4 K M Generate the run command https://quantized.uk/tools/cli-gen/?model=k2-horizon-7b&quant=Q4 K M How to actually run this Deployment guides for this model and this class of hardware. This page's figures change when the model or the runtime does.Last updated 2026-10-23 RSS → /feed.xml https://quantized.uk/feed.xml