Magic Tools
LLM VRAM Calculator (all models)

Can You Run Mistral Leanstral 1.5 (119B-A6B MoE)? VRAM Requirements

Mistral Leanstral 1.5 (119B-A6B MoE) has 119B total parameters (MoE, 6B active per token). Running it at Q4_K_M (GGUF) with 16K context takes roughly 73.4 GB of memory (67.6 GB weights + 0.4 GB KV cache + runtime overhead). The minimum viable hardware is about A100 / H100 80GB. All numbers are planning estimates, verified 2026-09-05.

⚠ Some architecture details of this model are estimated — treat results as ballpark figures.

VRAM by quantization (16K context)

QuantizationWeightsTotal neededMinimum hardware
FP16 / BF16222 GB240 GBMac M3 Ultra 512GB
FP8111 GB120 GBH200 141GB
Q8_0 (GGUF)117 GB127 GBH200 141GB
Q6_K (GGUF)90.9 GB98.5 GBMac 128GB unified
Q5_K_M (GGUF)78.7 GB85.3 GBMac 128GB unified
MXFP458.7 GB63.8 GBA100 / H100 80GB
NVFP458.7 GB63.8 GBA100 / H100 80GB
Q4_K_M (GGUF)recommended67.6 GB73.4 GBA100 / H100 80GB
Q3_K_M (GGUF)52.1 GB56.6 GBMac 64GB unified
Q2_K (GGUF)38.8 GB42.2 GBMac 64GB unified

How context length changes memory (Q4_K_M (GGUF))

ContextKV cacheTotal needed
4K0.1 GB73.1 GB
16K0.4 GB73.4 GB
64K1.4 GB74.4 GB
128K2.8 GB75.8 GB
256K5.6 GB78.6 GB
1M21.5 GB94.5 GB

KV cache grows linearly with context; FP8 KV cache halves it again (try it in the calculator below).

Customize the estimate

Back

LLM VRAM Calculator — Can I Run It?

Estimate how much GPU memory (VRAM) you need to run open-weight LLMs like Kimi K3, DeepSeek R1, Qwen3, or Llama locally. Pick a model, quantization, and context length — the calculator adds up weights, KV cache, and runtime overhead, then shows which GPUs or Macs can fit it. Runs entirely in your browser: no upload, no signup.

119B total params · 6B active (MoE) · max 1M context · specs partially estimated

Recommended balance · ~0.61 bytes/param

Estimated memory needed

75.8 GB

Model weights67.6 GB
KV cache (131,072 tokens)2.8 GB
Runtime overhead5.4 GB

Architecture details for this model are estimated — treat results as a ballpark.

Will it fit?

RTX 3060 12GB7× needed
RTX 4060 Ti 16GB6× needed
RTX 3090 / 4090 24GB4× needed
RTX 5090 32GB3× needed
A100 40GB3× needed
A100 / H100 80GB2× needed
H200 141GB✓ fits
AMD MI300X 192GB✓ fits
B200 192GB✓ fits
Mac 24GB unified✗ too big
Mac 36GB unified✗ too big
Mac 64GB unified✗ too big
Mac 128GB unified✓ fits
Mac M3 Ultra 512GB✓ fits

Assumes ~92% of device memory is usable. Multi-GPU counts are for tensor/pipeline parallel serving (vLLM, SGLang); Apple Silicon uses unified memory via llama.cpp or MLX.

FAQ

How much VRAM does Mistral Leanstral 1.5 (119B-A6B MoE) need?

About 73.4 GB at the recommended Q4_K_M (GGUF) quantization with 16K context: 67.6 GB for weights, 0.4 GB for KV cache, plus runtime overhead. Longer context grows the KV cache.

What is the minimum hardware for Mistral Leanstral 1.5 (119B-A6B MoE)?

Roughly A100 / H100 80GB, assuming 92% of device memory is usable. Lower-end setups can try more aggressive quantization (Q3/Q2) at a noticeable quality cost.

Can I run Mistral Leanstral 1.5 (119B-A6B MoE) on a Mac?

Yes. At Q4_K_M (GGUF) with 16K context it needs about 73.4 GB, which fits the unified memory of a Mac M3 Ultra 512GB via llama.cpp or MLX.

Which quantization should I use for Mistral Leanstral 1.5 (119B-A6B MoE)?

Q4_K_M is the recommended balance of size and quality; with headroom, Q6_K or Q8_0 reduce quality loss further.

VRAM requirements for other models