Model datasheet · Llama 3.3
Llama 3.3 70B
The largest dense model in this catalogue — everything above it is a sparse MoE. Best instruction-following evidence on the site at IFEval 92.1, and it needs a 96GB machine to be comfortable at any real context, because its KV cache costs 10GB at 32K before the weights are counted.
- Vendor
- Meta
- Architecture
- Dense · 70B
- Context
- 131,072 tokens
- License
- Llama 3.3 Community License
- Released
- 2024-12-06
- Vision
- No
→ GGUF (llama.cpp / LM Studio / Ollama) → MLX (Apple Silicon)
§1 Characteristics by quantization band
data checked Aug 2026
- quant-degradation-community — community consensus @ Q3_K_M · aggregated · 2026-08-30
Editorial derivation: two points down. 3-bit on a 70B still beats 4-bit on many smaller models, which is the argument for running one at all.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q3_K_M · aggregated · 2026-08-30
Editorial derivation: two points down from the full band.
Q4–Q5 — 4–5 bit
42.5GB weights · e.g. Q4_K_M , mlx-4bit + KV: 2.5GB at 8K · 10GB at 32K · 40GB at 128Kdata checked Aug 2026
- quant-degradation-community — community consensus @ Q4_K_M · aggregated · 2026-08-30
Editorial derivation: one point down. At 42.5GB this is the only band most people will realistically run, and large dense models tolerate 4-bit better than small ones.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q4_K_M · aggregated · 2026-08-30
Editorial derivation: one point down; multi-step arithmetic is the first thing 4-bit costs you.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q4_K_M · aggregated · 2026-08-30
Editorial derivation: one point down from the full band.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q6_K · aggregated · 2026-08-30
Editorial derivation: 6-bit is near-lossless, and a 70B has more redundancy to spare than anything else here. Carried unchanged.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q6_K · aggregated · 2026-08-30
Editorial derivation: carried from the full band.
FP16 — full precision (fp16/bf16)
141.1GB weights · e.g. bf16 + KV: 2.5GB at 8K · 10GB at 32K · 40GB at 128Kdata checked Aug 2026
- vendor-model-card — IFEval = 92.1 @ bf16 · vendor-reported · 2026-08-30
The highest instruction-following figure on this site, on a dimension only a third of the catalogue has any evidence for at all. IFEval is program-checkable, so there is less room for interpretation than most benchmarks.
data checked Aug 2026
- vendor-model-card — MATH (CoT) = 77 @ bf16 · vendor-reported · 2026-08-30
MGSM 91.1, MMLU (CoT) 86.0, MMLU-Pro 68.9. GPQA Diamond is only 50.5 — well behind the 2026 models here, which is what two years of progress looks like on graduate science questions.
data checked Aug 2026
- vendor-model-card — HumanEval = 88.4 @ bf16 · vendor-reported · 2026-08-30
MBPP EvalPlus 87.6. Scored well below those numbers on purpose: HumanEval is saturated and predates the agentic benchmarks the 2026 models are measured on, and this model has no SWE-bench or Terminal-Bench figure to compare against them.
data checked Aug 2026
- vendor-model-card — BFCL v2 = 77.3 @ bf16 · vendor-reported · 2026-08-30
Measured on BFCL v2; most entries here quote v3 or v4, which are not directly comparable.
§2 Known issues & what fixes them
Eighty layers with eight KV heads and no sliding window or linear attention: 320KB of cache per token, the most expensive in this catalogue. That is 2.5GB at 8K, 10GB at 32K and 40GB at 128K — on top of 42.5GB of 4-bit weights. Filling the advertised 128K window needs more memory for the cache than most machines have in total.
Retrieve rather than fill the window. On this model the context is what breaks your memory budget, not the weights.
Inverted advice: on a 64GB machine, dropping from Q4_K_M to Q3_K_M buys 8GB of weights, which is 25K more tokens of context. The quant you can afford depends on the context you need.
Evidence · 1 source · anecdotal
- Llama 3.3 70B config.json — 80 layers, 8 KV heads, head_dim 128, no sliding window (vendor, 2026-08-30)
Released December 2024 and measured on the benchmarks of that moment — HumanEval, MBPP, BFCL v2. It has no SWE-bench Verified or Terminal-Bench figure, so it cannot be compared with the 2026 agentic models on the work people now use these for. Where the comparison does exist it shows its age: GPQA Diamond 50.5 against 84–88 for the current 27–31B models.
Not a defect to fix. It remains the strongest instruction-follower here; it is simply not the model to reach for on agentic coding.
Evidence · 1 source · anecdotal
- Llama 3.3 70B evaluation table — HumanEval, MBPP, BFCL v2, GPQA 50.5 (vendor, 2026-08-30)
Llama 3.3 Community License, not Apache-2.0 or MIT. Commercial use is allowed but the terms carry conditions, including an attribution requirement and a monthly-active-user threshold above which a separate licence is needed.
Read the licence before shipping on it. If a permissive licence is a hard requirement, the Apache-2.0 and MIT models here are the alternatives.
Evidence · 1 source · anecdotal
- Llama 3.3 Community License Agreement (vendor, 2026-08-30)