Does It Run Local?

← All models

nvidia · observed 22 Oct 2026

Public-source support evidence

Llama-3.1-Nemotron-70B-Instruct-HF

Llama-3.1-Nemotron-70B-Instruct-HF is listed for local download in Ollama. A separately observed community Q4_K_M GGUF gives an estimated memory budget of about 53 GB; actual use depends on runtime and context settings.

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Llama-3.1-Nemotron-70B-Instruct-HF is a text generation model published by nvidia on Hugging Face. We have not written a summary yet; see the model card ↗

View source model ↗

SUPPORT EVIDENCE

Runtime status

llama.cpp

Architecture listed

The model config architecture is listed in this runtime registry. This is family/architecture evidence only; exact checkpoint loading, model-specific configuration, hardware, and generation were not tested.

Checked 2026-10-22 14:52 UTC

Evidence source ↗

Ollama

In release

In release. Ollama public library page exposes this exact size variant; catalog availability only, not hardware-tested support.

Checked 2026-10-22 17:03 UTC

Evidence source ↗

LM Studio

Upload available

A current public GGUF upload with an exact base_model match was observed. Upload availability only; this model was not loaded or hardware-tested.

Checked 2026-10-22 17:03 UTC

Evidence source ↗

MLX / mlx-lm

Upload available

A current public MLX upload with an exact base_model match was observed. Upload availability only; this model was not loaded or hardware-tested.

Checked 2026-10-22 17:03 UTC

Evidence source ↗

vLLM

Architecture listed

The model config architecture is listed in this runtime registry. This is family/architecture evidence only; exact checkpoint loading, model-specific configuration, hardware, and generation were not tested.

Checked 2026-10-22 14:52 UTC

Evidence source ↗

MLX community uploads may target mlx-vlm; an upload observation does not establish mlx-lm compatibility.

MEMORY ESTIMATES

Which file should I grab?

16 GB capacity estimate

Which file should I grab?

No observed complete artifact currently qualifies.

Unknown: no observed complete artifact fits this capacity with documented headroom.

24 GB capacity estimate

Which file should I grab?

IQ1_M · 16.8 GB observed ↗

Observed artifact size plus 20% headroom and 1.5 GB runtime allowance. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.

32 GB capacity estimate

Which file should I grab?

IQ2_M · 24.1 GB observed ↗

Observed artifact size plus 20% headroom and 1.5 GB runtime allowance. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.

128 GB capacity estimate

Which file should I grab?

Q8_0 · 75.0 GB observed ↗

Observed artifact size plus 20% headroom and 1.5 GB runtime allowance. Fit is an estimate; compatibility, speed, context length and hardware have not been tested. Link points to shard 1; all 2 linked shards are required.

Memory estimates are the observed file size plus fixed headroom (20% plus 1.5 GB runtime allowance); real needs also depend on context length, KV cache and runtime settings. Fit is an estimate; it does not establish runtime compatibility, speed, context length, or hardware performance. Text-weights-only estimates do not include a projector or total vision memory where unknown.

Terms: a quant is a lower-precision version of the weights; GGUF is a file format used by llama.cpp and compatible apps; MLX targets Apple silicon; vLLM is a model-serving engine for NVIDIA GPUs; the KV cache is stored attention state that grows with context length. Terms explained ↗

OBSERVED FILES

Quant uploads

Sizes and file groups come from the listed uploader repositories. A size is marked as an estimated fit only for a complete observed GGUF quant group.

UploaderFormat & quantObserved sizeEstimated fitFiles
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ1_M16.8 GB24 GB, 32 GB, 128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ2_M24.1 GB32 GB, 128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ2_XS21.1 GB32 GB, 128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ2_XXS19.1 GB32 GB, 128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ3_M31.9 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ3_XXS27.5 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · IQ4_XS37.9 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q2_K26.4 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q2_K_L27.4 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q3_K_L37.1 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q3_K_M34.3 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q3_K_S30.9 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q3_K_XL38.1 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q4_040.1 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q4_K_L43.3 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q4_K_M42.5 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q4_K_S40.3 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q5_K_L50.6 GB128 GBEstimate only; requires the complete GGUF quant group.
2 files
Complete observed GGUF quant group; all 2 shard(s) are required.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q5_K_M49.9 GB128 GBEstimate only; requires the complete GGUF quant group.
2 files
Complete observed GGUF quant group; all 2 shard(s) are required.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q5_K_S48.7 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q6_K57.9 GB128 GBEstimate only; requires the complete GGUF quant group.
2 files
Complete observed GGUF quant group; all 2 shard(s) are required.
bartowskibartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q8_075.0 GB128 GBEstimate only; requires the complete GGUF quant group.
2 files
Complete observed GGUF quant group; all 2 shard(s) are required.
lmstudio-communitylmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q3_K_L37.1 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
lmstudio-communitylmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q4_K_M42.5 GB128 GBEstimate only; requires the complete GGUF quant group.
1 file
Complete observed GGUF quant file.
lmstudio-communitylmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q6_K57.9 GB128 GBEstimate only; requires the complete GGUF quant group.
2 files
Complete observed GGUF quant group; all 2 shard(s) are required.
lmstudio-communitylmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF ↗Observed 22 Oct 2026GGUF · Q8_075.0 GB128 GBEstimate only; requires the complete GGUF quant group.
2 files
Complete observed GGUF quant group; all 2 shard(s) are required.
mlx-communitymlx-community/nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit ↗Observed 22 Oct 2026MLX · Quant unknownSize unknownUnknownUnknown: completeness or a complete GGUF quant group was not verified.
8 files
Observed weight file metadata; completeness unavailable without index/config verification.
mlx-communitymlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16 ↗Observed 22 Oct 2026MLX · Quant unknownSize unknownUnknownUnknown: completeness or a complete GGUF quant group was not verified.
28 files
Observed weight file metadata; completeness unavailable without index/config verification.

CURATED TRACKING

Known issues

No curated issues verified for this snapshot. An empty list does not mean there are no bugs.

HARDWARE NOTES

Hardware testing planned

No execution or benchmark results are published for this model yet.