Llama Krikri 8B Instruct — Hardware Requirements & GPU Compatibility
Chat
Llama Krikri 8B Instruct is a 8.2B-parameter open language model from ilsp in the Llama family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 5.49 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~119 tok/s · 128K)Macs from 16 GB (Q4_K_M · ~26 tok/s)
Llama 3.1 Community
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Llama Krikri 8B Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve ilsp/Llama-Krikri-8B-Instruct --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~108 tok/s
- generation speed
- Cost per 1M output tokens
- $0.31
- per 1M output tokens
How Much VRAM Does Llama Krikri 8B Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.0 GB | 8.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~162 tok/s | |
| 4.6 GB | 8.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~143 tok/s | |
| 5.5 GB | 9.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~119 tok/s | |
| 6.4 GB | 10.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~102 tok/s | |
| 7.3 GB | 11.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 64K context · ~89 tok/s | |
| 8.8 GB | 12.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 64K context · ~75 tok/s | |
| 17.0 GB | 21 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~39 tok/s |
Selected Q4_K_M
4-bit medium quantization7.4GBat 16K context
- Weights
- 4.9 GB
- KV cache
- 2.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.6 GB free · ~119 tok/s
≥50 tok/s needs ≥422 GB/s · RTX 5090 ~212, RTX 3090 Ti ~119
Which Hardware Can Run Llama Krikri 8B Instruct?
Q4_K_M · 5.5 GBLlama Krikri 8B Instruct (Q4_K_M) requires 5.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 131K context window can add up to 16.9 GB, bringing total usage to 22.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Llama Krikri 8B Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 0.6 GB free · up to 16K ctx
16 GPUs · 1 device family
RTX 3080~90Simulate output on RTX 3080RTX 2080 Ti~73Simulate output on RTX 2080 TiRTX 3070 Ti~72Simulate output on RTX 3070 TiOrin Nano~12Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 12.6 GB free · up to 64K ctx
1 GPU
RX 7900 XT~87Simulate output on RX 7900 XT32–40 GB
fits · 24.6 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~212Simulate output on RTX 5090M5 Max36 GB~59Simulate output on Mac Studio M5 Max (36 GB)M532 GB~20Simulate output on MacBook Air 13" M5 (32 GB)Orin~24Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~16Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Llama Krikri 8B Instruct
Llama family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite Switch 4.1 8BIBM | — | 8.4 GB | ~111 | same size |
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | same size |
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- ilsp
- Family
- Llama
- Parameters
- 8.2B
- Architecture
- LlamaForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 149,248
- Release Date
- 2025-02-07
- License
- Llama 3.1 Community
Frequently Asked Questions
How much VRAM does Llama Krikri 8B Instruct need?
Llama Krikri 8B Instruct requires 5.5 GB of VRAM at Q4_K_M, or 17.0 GB at BF16. Full 131K context adds up to 16.9 GB (22.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.2B × 4.8 bits ÷ 8 = 4.9 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 17.5 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Llama Krikri 8B Instruct?
For Llama Krikri 8B Instruct, Q4_K_M (5.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (6.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Llama Krikri 8B Instruct on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Llama Krikri 8B Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run Llama Krikri 8B Instruct locally?
Yes — Llama Krikri 8B Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Llama Krikri 8B Instruct?
At Q4_K_M, Llama Krikri 8B Instruct can reach ~874 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~119 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 5.49 × 0.65 = ~947 tok/s
Estimated speed at Q4_K_M (5.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Llama Krikri 8B Instruct?
At Q4_K_M, the download is about 4.92 GB. The full-precision BF16 version is 16.40 GB. The smallest option (Q2_K) is 3.49 GB.
Which GPUs can run Llama Krikri 8B Instruct?
52 consumer GPUs can run Llama Krikri 8B Instruct at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Llama Krikri 8B Instruct?
151 devices with unified memory can run Llama Krikri 8B Instruct at Q4_K_M (5.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.