K2-Horizon 7B hardware requirements
What is K2-Horizon 7B?
K2-Horizon 7B is the mid-sized dense model of the K2-Horizon family, which IFM (Institute of Foundation Models) released in September 2026. Its card calls it a 7B-core model, though the full weights come to about 9B parameters, and reports agentic, coding, long-context and reasoning benchmarks. Thinking is always on, with reasoning_effort setting its depth. The native context is 524,288 tokens, and the Apache 2.0 license allows commercial use.
About the model
- Parameters
- 9B
- Attention
- Full attention
- Max context
- 524,288 tokens
- Released
- 2026-09-01
- Model card
- K2-Horizon 7B on Hugging Face
Other sizes in this series
| Model | Parameters | Baseline quant | Memory needed (8k) | GeForce RTX 4060 | GeForce RTX 5060 Ti 16GB | GeForce RTX 3090 |
|---|---|---|---|---|---|---|
| K2-Horizon 7Bthis model | 9B | Q4_K_M | 6.8 GB | Runs well | Runs great | Runs great |
| K2-Horizon MoVA 36B-A4B | 37.44B total · 4B active (MoE) | Q4_K_M | 24.2 GB | Runs slowly | Runs well | Runs well |
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q4_K_Mbaseline | 5.59 GB | Good balance | Official GGUF · IFM |
| Q8_0 | 9.57 GB | Near-lossless | Official GGUF · IFM |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q4_K_M | 6.1 | 6.8 | 8.1 | 10.6 | 15.8 | 26.0 | 46.6 |
| Q8_0 | 9.6 | 10.3 | 11.5 | 14.1 | 19.2 | 29.5 | 50.0 |
Which GPUs can run K2-Horizon 7B?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs great | est. 184.5 tok/s162.4–206.7calibrated estimate ±12% | Q4_K_M | 7.4 / 32.0 GB | Full GPU | up to 128k | — | $4,200 street (as of 2026-08-09) |
| Radeon RX 7900 XTX | Runs great | est. 107.3 tok/s94.4–120.2calibrated estimate ±12% | Q4_K_M | 7.4 / 24.0 GB | Full GPU | up to 64k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 103.8 tok/s91.3–116.3calibrated estimate ±12% | Q4_K_M | 7.4 / 24.0 GB | Full GPU | up to 64k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 103.8 tok/s91.3–116.3calibrated estimate ±12% | Q4_K_M | 7.4 / 24.0 GB | Full GPU | up to 64k | — | $2,755 street (as of 2026-08-09) |
| Apple M5 Ultra · 96 GB | Runs great | est. 103.0 tok/s82.4–123.6calibrated estimate ±20% | Q4_K_M | 7.4 / 67.2 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 5080 | Runs great | est. 98.9 tok/s87.0–110.7calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs great | est. 96.4 tok/s84.8–107.9calibrated estimate ±12% | Q4_K_M | 7.4 / 24.0 GB | Full GPU | up to 64k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 93.9 tok/s82.6–105.2calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 32k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 92.3 tok/s81.2–103.3calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 92.3 tok/s81.2–103.3calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 92.3 tok/s81.2–103.3calibrated estimate ±12% | Q4_K_M | 7.4 / 24.0 GB | Full GPU | up to 64k | — | — |
| Radeon RX 7900 XT | Runs great | est. 89.4 tok/s78.7–100.2calibrated estimate ±12% | Q4_K_M | 7.4 / 20.0 GB | Full GPU | up to 64k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 78.3 tok/s68.9–87.6calibrated estimate ±12% | Q4_K_M | 7.4 / 10.0 GB | Full GPU | up to 16k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 75.8 tok/s66.7–84.9calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $999 launch MSRP |
| GeForce RTX 4080 | Runs great | est. 73.8 tok/s65.0–82.7calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $1,199 launch MSRP |
| Radeon RX 9070 | Runs great | est. 72.1 tok/s63.5–80.8calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 72.1 tok/s63.5–80.8calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Runs great | est. 69.8 tok/s61.4–78.1calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 69.2 tok/s60.9–77.5calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 69.2 tok/s60.9–77.5calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 32k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 69.2 tok/s60.9–77.5calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 32k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 68.7 tok/s54.9–82.4calibrated estimate ±20% | Q4_K_M | 7.4 / 67.2 GB | Unified memory | up to 64k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 68.6 tok/s54.9–82.4calibrated estimate ±20% | Q4_K_M | 7.4 / 33.6 GB | Unified memory | up to 64k | — | — |
| Apple M2 Ultra · 64 GB | Runs great | est. 67.1 tok/s53.7–80.5calibrated estimate ±20% | Q4_K_M | 7.4 / 44.8 GB | Unified memory | up to 32k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 63.4 tok/s55.8–71.0calibrated estimate ±12% | Q4_K_M | 7.4 / 11.0 GB | Full GPU | up to 16k | — | $999 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 61.0 tok/s48.8–73.3calibrated estimate ±20% | Q4_K_M | 7.4 / 33.6 GB | Unified memory | up to 32k | — | — |
| GeForce RTX 4090 Laptop | Runs great | est. 59.3 tok/s52.2–66.4calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | — |
| GeForce RTX 4070 | Runs great | est. 51.9 tok/s45.7–58.1calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 32k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 51.9 tok/s45.7–58.1calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 32k | — | $599 launch MSRP |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 51.4 tok/s41.1–61.7calibrated estimate ±20% | Q4_K_M | 7.4 / 25.2 GB | Unified memory | up to 32k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 49.8 tok/s34.9–64.8theoretical estimate ±30% | Q4_K_M | 7.4 / 11.0 GB | Full GPU | up to 16k | — | $699 launch MSRP |
| GeForce RTX 3070 | Runs great | est. 46.1 tok/s40.6–51.7calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 46.1 tok/s40.6–51.7calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Runs great | est. 46.1 tok/s40.6–51.7calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs great | est. 46.1 tok/s40.6–51.7calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | $429 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 45.8 tok/s36.7–55.0calibrated estimate ±20% | Q4_K_M | 7.4 / 25.2 GB | Unified memory | up to 16k | — | — |
| GeForce RTX 4080 Laptop | Runs great | est. 44.5 tok/s39.1–49.8calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 16k | — | — |
| Intel Arc B580 | Runs great | est. 39.6 tok/s31.7–47.5calibrated estimate ±20% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 16k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs great | est. 37.1 tok/s32.6–41.5calibrated estimate ±12% | Q4_K_M | 7.4 / 12.0 GB | Full GPU | up to 16k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 36.0 tok/s31.7–40.3calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 16k | — | $449 street (as of 2026-08-09) |
| Apple M5 Pro · 24 GB | Runs great | est. 34.3 tok/s27.5–41.2calibrated estimate ±20% | Q4_K_M | 7.4 / 16.8 GB | Unified memory | up to 8k | — | — |
| NVIDIA DGX Spark · 64 GB | Runs great | est. 31.3 tok/s25.1–37.6calibrated estimate ±20% | Q4_K_M | 7.4 / 48.2 GB | Unified memory | up to 8k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 30.9 tok/s24.7–37.1calibrated estimate ±20% | Q4_K_M | 7.4 / 22.4 GB | Unified memory | up to 8k | — | $1,999 launch MSRP (128 GB) |
| Apple M4 Pro · 24 GB | Runs great | est. 30.5 tok/s24.4–36.6calibrated estimate ±20% | Q4_K_M | 7.4 / 16.8 GB | Unified memory | up to 8k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs well | est. 29.7 tok/s26.1–33.2calibrated estimate ±12% | Q4_K_M | 7.4 / 16.0 GB | Full GPU | up to 32k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs well | est. 29.7 tok/s26.1–33.2calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs well | est. 28.0 tok/s24.6–31.4calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs well | est. 26.4 tok/s23.2–29.5calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | — |
| GeForce RTX 4070 Laptop | Runs well | est. 26.4 tok/s23.2–29.5calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | — |
| GeForce RTX 3050 8GB | Runs well | est. 23.1 tok/s20.3–25.8calibrated estimate ±12% | Q4_K_M | 7.4 / 8.0 GB | Full GPU | up to 8k | — | $249 launch MSRP |
| Apple M5 · 16 GB | Runs well | est. 17.2 tok/s13.7–20.6calibrated estimate ±20% | Q4_K_M | 7.4 / 11.2 GB | Unified memory | up to 16k | — | — |
| Apple M6 · 16 GB | Runs well | est. 17.2 tok/s13.7–20.6calibrated estimate ±20% | Q4_K_M | 7.4 / 11.2 GB | Unified memory | up to 16k | — | — |
| Apple M4 · 16 GB | Runs well | est. 13.4 tok/s10.7–16.1calibrated estimate ±20% | Q4_K_M | 7.4 / 11.2 GB | Unified memory | up to 8k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 7.1 tok/s5.6–8.5calibrated estimate ±20% | Q4_K_M | 6.8 GB RAM | CPU only | up to 32k | — | — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 6.6 tok/s5.3–7.9calibrated estimate ±20% | Q4_K_M | 6.8 GB RAM | CPU only | up to 32k | — | — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 3.8 tok/s3.0–4.5calibrated estimate ±20% | Q4_K_M | 6.8 GB RAM | CPU only | up to 16k | — | — |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
- Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 37.1 tok/s (32.6–41.5, calibrated estimate ±12%).
Measured results for K2-Horizon 7B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does K2-Horizon 7B need?
At Q4_K_M the file is 5.59 GB; with 8k context a graphics card needs about 6.8 GB (weights 5.00 GB, KV cache 1.2 GB, compute buffer 0.6 GB). Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs K2-Horizon 7B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 37.1 tok/s (32.6–41.5, calibrated estimate ±12%).
Can K2-Horizon 7B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs well, est. 28.0 tok/s (24.6–31.4, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 46.1 tok/s (40.6–51.7, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 96.4 tok/s (84.8–107.9, calibrated estimate ±12%).
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.