L3 8B Stheno V3.2 — Hardware Requirements & GPU Compatibility
Chat
L3 8B Stheno V3.2 is a 8.0B-parameter open language model from Sao10K. It supports a context window of up to 8,192 tokens. At Q4_K_M it needs about 5.39 GB of VRAM — see which GPUs and Macs can run it below.
14.3K downloads
412 likesSpecifications
- Publisher
- Sao10K
- Parameters
- 8.0B
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 128,256
- Release Date
- 2024-06-07
- License
- CC BY-NC 4.0
Get Started
HuggingFace
How Much VRAM Does L3 8B Stheno V3.2 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.0 GB | 4.8 GB | 3.41 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.1 GB | 4.9 GB | 3.51 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.5 GB | 5.3 GB | 3.91 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 5.4 GB | 6.2 GB | 4.82 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 6.3 GB | 7.1 GB | 5.72 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 7.2 GB | 8 GB | 6.62 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 8.6 GB | 9.4 GB | 8.03 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run L3 8B Stheno V3.2?
Q4_K_M · 5.4 GBL3 8B Stheno V3.2 (Q4_K_M) requires 5.4 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 8K context window can add up to 0.8 GB, bringing total usage to 6.2 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run L3 8B Stheno V3.2?
Q4_K_M · 5.4 GB33 devices with unified memory can run L3 8B Stheno V3.2, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does L3 8B Stheno V3.2 need?
L3 8B Stheno V3.2 requires 5.4 GB of VRAM at Q4_K_M, or 8.6 GB at Q8_0. Full 8K context adds up to 0.8 GB (6.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.0B × 4.8 bits ÷ 8 = 4.8 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.4 GB (at full 8K context)
VRAM usage by quantization
Q4_K_M5.4 GBQ4_K_M + full context6.2 GB- What's the best quantization for L3 8B Stheno V3.2?
For L3 8B Stheno V3.2, Q4_K_M (5.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (6.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XS at 3.0 GB.
VRAM requirement by quantization
IQ2_XS3.0 GBIQ3_XS3.9 GBQ3_K_M4.5 GBQ4_K_M ★5.4 GBQ5_K_S6.1 GBQ8_08.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run L3 8B Stheno V3.2 on a Mac?
L3 8B Stheno V3.2 requires at least 3.0 GB at IQ2_XS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run L3 8B Stheno V3.2 locally?
Yes — L3 8B Stheno V3.2 can run locally on consumer hardware. At Q4_K_M quantization it needs 5.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is L3 8B Stheno V3.2?
At Q4_K_M, L3 8B Stheno V3.2 can reach ~541 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~122 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 5.4 × 0.55 = ~541 tok/s
Estimated speed at Q4_K_M (5.4 GB)
~541 tok/s~122 tok/s~404 tok/s~334 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of L3 8B Stheno V3.2?
At Q4_K_M, the download is about 4.82 GB. The full-precision Q8_0 version is 8.03 GB. The smallest option (IQ2_XS) is 2.41 GB.
- Which GPUs can run L3 8B Stheno V3.2?
35 consumer GPUs can run L3 8B Stheno V3.2 at Q4_K_M (5.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run L3 8B Stheno V3.2?
33 devices with unified memory can run L3 8B Stheno V3.2 at Q4_K_M (5.4 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.